Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707720
Evgeny A. Stepanov, Ilya Kashkarev, Ali Orkan Bayer, G. Riccardi, Arindam Ghosh
Automatic cross-language Spoken Language Understanding porting is plagued by two limitations. First, SLU are usually trained on limited domain corpora. Second, language pair resources (e.g. aligned corpora) are scarce or unmatched in style (e.g. news vs. conversation). We present experiments on automatic style adaptation of the input for the translation systems and their output for SLU. We approach the problem of scarce aligned data by adapting the available parallel data to the target domain using limited in-domain and larger web crawled close-to-domain corpora. SLU performance is optimized by reranking its output with Recurrent Neural Network-based joint language model. We evaluate end-to-end SLU porting on close and distant language pairs: Spanish - Italian and Turkish - Italian; and achieve significant improvements both in translation quality and SLU performance.
{"title":"Language style and domain adaptation for cross-language SLU porting","authors":"Evgeny A. Stepanov, Ilya Kashkarev, Ali Orkan Bayer, G. Riccardi, Arindam Ghosh","doi":"10.1109/ASRU.2013.6707720","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707720","url":null,"abstract":"Automatic cross-language Spoken Language Understanding porting is plagued by two limitations. First, SLU are usually trained on limited domain corpora. Second, language pair resources (e.g. aligned corpora) are scarce or unmatched in style (e.g. news vs. conversation). We present experiments on automatic style adaptation of the input for the translation systems and their output for SLU. We approach the problem of scarce aligned data by adapting the available parallel data to the target domain using limited in-domain and larger web crawled close-to-domain corpora. SLU performance is optimized by reranking its output with Recurrent Neural Network-based joint language model. We evaluate end-to-end SLU porting on close and distant language pairs: Spanish - Italian and Turkish - Italian; and achieve significant improvements both in translation quality and SLU performance.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"34 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125451802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707726
Ramón Fernández Astudillo
This paper presents a closed form solution relating the joint distributions of corrupted and clean speech in the short-time Fourier Transform (STFT) and Mel-Frequency Cepstral Coefficient (MFCC) domains. This makes possible a tighter integration of STFT domain speech enhancement and feature and model-compensation techniques for robust automatic speech recognition. The approach directly utilizes the conventional speech distortion model for STFT speech enhancement, allowing for low cost, single pass, causal implementations. Compared to similar uncertainty propagation approaches, it provides the full joint distribution, rather than just the posterior distribution, which provides additional model compensation possibilities. The method is exemplified by deriving an MMSE-MFCC estimator from the propagated joint distribution. It is shown that similar performance to that of STFT uncertainty propagation (STFT-UP) can be obtained on the AURORA4, while deriving the full joint distribution.
{"title":"A propagation approach to modelling the joint distributions of clean and corrupted speech in the Mel-Cepstral domain","authors":"Ramón Fernández Astudillo","doi":"10.1109/ASRU.2013.6707726","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707726","url":null,"abstract":"This paper presents a closed form solution relating the joint distributions of corrupted and clean speech in the short-time Fourier Transform (STFT) and Mel-Frequency Cepstral Coefficient (MFCC) domains. This makes possible a tighter integration of STFT domain speech enhancement and feature and model-compensation techniques for robust automatic speech recognition. The approach directly utilizes the conventional speech distortion model for STFT speech enhancement, allowing for low cost, single pass, causal implementations. Compared to similar uncertainty propagation approaches, it provides the full joint distribution, rather than just the posterior distribution, which provides additional model compensation possibilities. The method is exemplified by deriving an MMSE-MFCC estimator from the propagated joint distribution. It is shown that similar performance to that of STFT uncertainty propagation (STFT-UP) can be obtained on the AURORA4, while deriving the full joint distribution.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128395459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707769
Shilin Liu, K. Sim
Building a good Automatic Speech Recognition (ASR) system with limited resources is a very challenging task due to the existing many speech variations. Multilingual and cross-lingual speech recognition techniques are commonly used for this task. This paper investigates the recently proposed Temporally Varying Weight Regression (TVWR) method for cross-lingual speech recognition. TVWR uses posterior features to implicitly model the long-term temporal structures in acoustic patterns. By leveraging on the well-trained foreign recognizers, high quality monophone/state posteriors can be easily incorporated into TVWR to boost the ASR performance on low-resource languages. Furthermore, multi-stream TVWR is proposed, where multiple sets of posterior features are used to incorporate richer (temporal and spatial) context information. Finally, a separate state-tying for the TVWR regression parameters is used to better utilize the more reliable posterior features. Experimental results are evaluated for English and Malay speech recognition with limited resources. By using the Czech, Hungarian and Russian posterior features, TVWR was found to consistently outperform the tandem systems trained on the same features.
{"title":"Multi-stream temporally varying weight regression for cross-lingual speech recognition","authors":"Shilin Liu, K. Sim","doi":"10.1109/ASRU.2013.6707769","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707769","url":null,"abstract":"Building a good Automatic Speech Recognition (ASR) system with limited resources is a very challenging task due to the existing many speech variations. Multilingual and cross-lingual speech recognition techniques are commonly used for this task. This paper investigates the recently proposed Temporally Varying Weight Regression (TVWR) method for cross-lingual speech recognition. TVWR uses posterior features to implicitly model the long-term temporal structures in acoustic patterns. By leveraging on the well-trained foreign recognizers, high quality monophone/state posteriors can be easily incorporated into TVWR to boost the ASR performance on low-resource languages. Furthermore, multi-stream TVWR is proposed, where multiple sets of posterior features are used to incorporate richer (temporal and spatial) context information. Finally, a separate state-tying for the TVWR regression parameters is used to better utilize the more reliable posterior features. Experimental results are evaluated for English and Malay speech recognition with limited resources. By using the Czech, Hungarian and Russian posterior features, TVWR was found to consistently outperform the tandem systems trained on the same features.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133916696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707717
Aanchan Mohan, R. Rose
This paper is concerned with the problem of building acoustic models for automatic speech recognition (ASR) using speech data from multiple languages. Techniques for multi-lingual ASR are developed in the context of the subspace Gaussian mixture model (SGMM)[2, 3]. Multi-lingual SGMM based ASR systems have been configured with shared subspace parameters trained from multiple languages but with distinct language dependent phonetic contexts and states[11, 12]. First, an approach for sharing state-level target language and foreign language SGMM parameters is described. Second, semi-tied covariance transformations are applied as an alternative to full-covariance Gaussians to make acoustic model training less sensitive to issues of insufficient training data. These techniques are applied to Hindi and Marathi language data obtained for an agricultural commodities dialog task in multiple Indian languages.
{"title":"Cross-lingual context sharing and parameter-tying for multi-lingual speech recognition","authors":"Aanchan Mohan, R. Rose","doi":"10.1109/ASRU.2013.6707717","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707717","url":null,"abstract":"This paper is concerned with the problem of building acoustic models for automatic speech recognition (ASR) using speech data from multiple languages. Techniques for multi-lingual ASR are developed in the context of the subspace Gaussian mixture model (SGMM)[2, 3]. Multi-lingual SGMM based ASR systems have been configured with shared subspace parameters trained from multiple languages but with distinct language dependent phonetic contexts and states[11, 12]. First, an approach for sharing state-level target language and foreign language SGMM parameters is described. Second, semi-tied covariance transformations are applied as an alternative to full-covariance Gaussians to make acoustic model training less sensitive to issues of insufficient training data. These techniques are applied to Hindi and Marathi language data obtained for an agricultural commodities dialog task in multiple Indian languages.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132744127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707716
Yun-Nung (Vivian) Chen, William Yang Wang, Alexander I. Rudnicky
Spoken dialogue systems typically use predefined semantic slots to parse users' natural language inputs into unified semantic representations. To define the slots, domain experts and professional annotators are often involved, and the cost can be expensive. In this paper, we ask the following question: given a collection of unlabeled raw audios, can we use the frame semantics theory to automatically induce and fill the semantic slots in an unsupervised fashion? To do this, we propose the use of a state-of-the-art frame-semantic parser, and a spectral clustering based slot ranking model that adapts the generic output of the parser to the target semantic space. Empirical experiments on a real-world spoken dialogue dataset show that the automatically induced semantic slots are in line with the reference slots created by domain experts: we observe a mean averaged precision of 69.36% using ASR-transcribed data. Our slot filling evaluations also indicate the promising future of this proposed approach.
{"title":"Unsupervised induction and filling of semantic slots for spoken dialogue systems using frame-semantic parsing","authors":"Yun-Nung (Vivian) Chen, William Yang Wang, Alexander I. Rudnicky","doi":"10.1109/ASRU.2013.6707716","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707716","url":null,"abstract":"Spoken dialogue systems typically use predefined semantic slots to parse users' natural language inputs into unified semantic representations. To define the slots, domain experts and professional annotators are often involved, and the cost can be expensive. In this paper, we ask the following question: given a collection of unlabeled raw audios, can we use the frame semantics theory to automatically induce and fill the semantic slots in an unsupervised fashion? To do this, we propose the use of a state-of-the-art frame-semantic parser, and a spectral clustering based slot ranking model that adapts the generic output of the parser to the target semantic space. Empirical experiments on a real-world spoken dialogue dataset show that the automatically induced semantic slots are in line with the reference slots created by domain experts: we observe a mean averaged precision of 69.36% using ASR-transcribed data. Our slot filling evaluations also indicate the promising future of this proposed approach.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130285528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707754
Jonas Gehring, Quoc Bao Nguyen, Florian Metze, A. Waibel
In this work, we propose several deep neural network architectures that are able to leverage data from multiple languages. Modularity is achieved by training networks for extracting high-level features and for estimating phoneme state posteriors separately, and then combining them for decoding in a hybrid DNN/HMM setup. This approach has been shown to achieve superior performance for single-language systems, and here we demonstrate that feature extractors benefit significantly from being trained as multi-lingual networks with shared hidden representations. We also show that existing mono-lingual networks can be re-used in a modular fashion to achieve a similar level of performance without having to train new networks on multi-lingual data. Furthermore, we investigate in extending these architectures to make use of language-specific acoustic features. Evaluations are performed on a low-resource conversational telephone speech transcription task in Vietnamese, while additional data for acoustic model training is provided in Pashto, Tagalog, Turkish, and Cantonese. Improvements of up to 17.4% and 13.8% over mono-lingual GMMs and DNNs, respectively, are obtained.
{"title":"DNN acoustic modeling with modular multi-lingual feature extraction networks","authors":"Jonas Gehring, Quoc Bao Nguyen, Florian Metze, A. Waibel","doi":"10.1109/ASRU.2013.6707754","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707754","url":null,"abstract":"In this work, we propose several deep neural network architectures that are able to leverage data from multiple languages. Modularity is achieved by training networks for extracting high-level features and for estimating phoneme state posteriors separately, and then combining them for decoding in a hybrid DNN/HMM setup. This approach has been shown to achieve superior performance for single-language systems, and here we demonstrate that feature extractors benefit significantly from being trained as multi-lingual networks with shared hidden representations. We also show that existing mono-lingual networks can be re-used in a modular fashion to achieve a similar level of performance without having to train new networks on multi-lingual data. Furthermore, we investigate in extending these architectures to make use of language-specific acoustic features. Evaluations are performed on a low-resource conversational telephone speech transcription task in Vietnamese, while additional data for acoustic model training is provided in Pashto, Tagalog, Turkish, and Cantonese. Improvements of up to 17.4% and 13.8% over mono-lingual GMMs and DNNs, respectively, are obtained.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125431380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707765
Keith D. Levin, Katharine Henry, A. Jansen, Karen Livescu
Measures of acoustic similarity between words or other units are critical for segmental exemplar-based acoustic models, spoken term discovery, and query-by-example search. Dynamic time warping (DTW) alignment cost has been the most commonly used measure, but it has well-known inadequacies. Some recently proposed alternatives require large amounts of training data. In the interest of finding more efficient, accurate, and low-resource alternatives, we consider the problem of embedding speech segments of arbitrary length into fixed-dimensional spaces in which simple distances (such as cosine or Euclidean) serve as a proxy for linguistically meaningful (phonetic, lexical, etc.) dissimilarities. Such embeddings would enable efficient audio indexing and permit application of standard distance learning techniques to segmental acoustic modeling. In this paper, we explore several supervised and unsupervised approaches to this problem and evaluate them on an acoustic word discrimination task. We identify several embedding algorithms that match or improve upon the DTW baseline in low-resource settings.
{"title":"Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings","authors":"Keith D. Levin, Katharine Henry, A. Jansen, Karen Livescu","doi":"10.1109/ASRU.2013.6707765","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707765","url":null,"abstract":"Measures of acoustic similarity between words or other units are critical for segmental exemplar-based acoustic models, spoken term discovery, and query-by-example search. Dynamic time warping (DTW) alignment cost has been the most commonly used measure, but it has well-known inadequacies. Some recently proposed alternatives require large amounts of training data. In the interest of finding more efficient, accurate, and low-resource alternatives, we consider the problem of embedding speech segments of arbitrary length into fixed-dimensional spaces in which simple distances (such as cosine or Euclidean) serve as a proxy for linguistically meaningful (phonetic, lexical, etc.) dissimilarities. Such embeddings would enable efficient audio indexing and permit application of standard distance learning techniques to segmental acoustic modeling. In this paper, we explore several supervised and unsupervised approaches to this problem and evaluate them on an acoustic word discrimination task. We identify several embedding algorithms that match or improve upon the DTW baseline in low-resource settings.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"645 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120876196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707741
Karel Veselý, M. Hannemann, L. Burget
In this paper we search for an optimal strategy for semi-supervised Deep Neural Network (DNN) training. We assume that a small part of the data is transcribed, while the majority of the data is untranscribed. We explore self-training strategies with data selection based on both the utterance-level and frame-level confidences. Further on, we study the interactions between semi-supervised frame-discriminative training and sequence-discriminative sMBR training. We found it beneficial to reduce the disproportion in amounts of transcribed and untranscribed data by including the transcribed data several times, as well as to do a frame-selection based on per-frame confidences derived from confusion in a lattice. For the experiments, we used the Limited language pack condition for the Surprise language task (Vietnamese) from the IARPA Babel program. The absolute Word Error Rate (WER) improvement for frame cross-entropy training is 2.2%, this corresponds to WER recovery of 36% when compared to the identical system, where the DNN is built on the fully transcribed data.
{"title":"Semi-supervised training of Deep Neural Networks","authors":"Karel Veselý, M. Hannemann, L. Burget","doi":"10.1109/ASRU.2013.6707741","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707741","url":null,"abstract":"In this paper we search for an optimal strategy for semi-supervised Deep Neural Network (DNN) training. We assume that a small part of the data is transcribed, while the majority of the data is untranscribed. We explore self-training strategies with data selection based on both the utterance-level and frame-level confidences. Further on, we study the interactions between semi-supervised frame-discriminative training and sequence-discriminative sMBR training. We found it beneficial to reduce the disproportion in amounts of transcribed and untranscribed data by including the transcribed data several times, as well as to do a frame-selection based on per-frame confidences derived from confusion in a lattice. For the experiments, we used the Limited language pack condition for the Surprise language task (Vietnamese) from the IARPA Babel program. The absolute Word Error Rate (WER) improvement for frame cross-entropy training is 2.2%, this corresponds to WER recovery of 36% when compared to the identical system, where the DNN is built on the fully transcribed data.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128043740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707698
Berlin Chen, Yi-Wen Chen, Kuan-Yu Chen, E. Jan
A part and parcel of any automatic speech recognition (ASR) system is language modeling (LM), which helps to constrain the acoustic analysis, guide the search through multiple candidate word strings, and quantify the acceptability of the final output hypothesis given an input utterance. Despite the fact that the n-gram model remains the predominant one, a number of novel and ingenious LM methods have been developed to complement or be used in place of the n-gram model. A more recent line of research is to leverage information cues gleaned from pseudo-relevance feedback (PRF) to derive an utterance-regularized language model for complementing the n-gram model. This paper presents a continuation of this general line of research and its main contribution is two-fold. First, we explore an alternative and more efficient formulation to construct such an utterance-regularized language model for ASR. Second, the utilities of various utterance-regularized language models are analyzed and compared extensively. Empirical experiments on a large vocabulary continuous speech recognition (LVCSR) task demonstrate that our proposed language models can offer substantial improvements over the baseline n-gram system, and achieve performance competitive to, or better than, some state-of-the-art language models.
{"title":"Effective pseudo-relevance feedback for language modeling in speech recognition","authors":"Berlin Chen, Yi-Wen Chen, Kuan-Yu Chen, E. Jan","doi":"10.1109/ASRU.2013.6707698","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707698","url":null,"abstract":"A part and parcel of any automatic speech recognition (ASR) system is language modeling (LM), which helps to constrain the acoustic analysis, guide the search through multiple candidate word strings, and quantify the acceptability of the final output hypothesis given an input utterance. Despite the fact that the n-gram model remains the predominant one, a number of novel and ingenious LM methods have been developed to complement or be used in place of the n-gram model. A more recent line of research is to leverage information cues gleaned from pseudo-relevance feedback (PRF) to derive an utterance-regularized language model for complementing the n-gram model. This paper presents a continuation of this general line of research and its main contribution is two-fold. First, we explore an alternative and more efficient formulation to construct such an utterance-regularized language model for ASR. Second, the utilities of various utterance-regularized language models are analyzed and compared extensively. Empirical experiments on a large vocabulary continuous speech recognition (LVCSR) task demonstrate that our proposed language models can offer substantial improvements over the baseline n-gram system, and achieve performance competitive to, or better than, some state-of-the-art language models.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131620207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-12-01DOI: 10.1109/ASRU.2013.6707710
J. Svec, P. Ircing, L. Smídl
The paper presents a novel approach to named entity detection from ASR lattices. Since the described method not only detects the named entities but also assigns a detailed semantic interpretation to them, we call our approach the semantic entity detection. All the algorithms are designed to use automata operations defined within the framework of weighted finite state transducers (WFST) - the ASR lattices are nowadays frequently represented as weighted acceptors. The expert knowledge about the semantics of the task at hand can be first expressed in the form of a context free grammar and then converted to the FST form. We use a WFST optimization to obtain compact representation of the ASR lattice. The WFST framework also allows to use the word confusion networks as another representation of multiple ASR hypotheses. That way we can use the full power of composition and optimization operations implemented in the OpenFST toolkit for our semantic entity detection algorithm. The devised method also employs the concept of a factor automaton; this approach allows us to overcome the need for a filler model and consequently makes the method more general. The paper includes experimental evaluation of the proposed algorithm and compares the performance obtained by using the one-best word hypothesis, optimized lattices and word confusion networks.
{"title":"Semantic entity detection from multiple ASR hypotheses within the WFST framework","authors":"J. Svec, P. Ircing, L. Smídl","doi":"10.1109/ASRU.2013.6707710","DOIUrl":"https://doi.org/10.1109/ASRU.2013.6707710","url":null,"abstract":"The paper presents a novel approach to named entity detection from ASR lattices. Since the described method not only detects the named entities but also assigns a detailed semantic interpretation to them, we call our approach the semantic entity detection. All the algorithms are designed to use automata operations defined within the framework of weighted finite state transducers (WFST) - the ASR lattices are nowadays frequently represented as weighted acceptors. The expert knowledge about the semantics of the task at hand can be first expressed in the form of a context free grammar and then converted to the FST form. We use a WFST optimization to obtain compact representation of the ASR lattice. The WFST framework also allows to use the word confusion networks as another representation of multiple ASR hypotheses. That way we can use the full power of composition and optimization operations implemented in the OpenFST toolkit for our semantic entity detection algorithm. The devised method also employs the concept of a factor automaton; this approach allows us to overcome the need for a filler model and consequently makes the method more general. The paper includes experimental evaluation of the proposed algorithm and compares the performance obtained by using the one-best word hypothesis, optimized lattices and word confusion networks.","PeriodicalId":265258,"journal":{"name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124045880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：