Incorporating language constraints in sub-word based speech recognition

A fast and memory-efficient N-gram language model lookup method for large vocabulary continuous speech recognition

This paper deals with the use of a stochastic context‐free grammar (SCFG) for large vocabulary continuous speech recognition; in particular, an SCFG with phrase‐level dependency rules is built. Unlike n‐gram models, the SCFG can describe not only local constraints but also global constraints pertaining to the sentence as a whole, thus making possible language models with great expressive power. However, the inside‐outside algorithm must be used for estimation of the SCFG parameters, which involves a great amount of calculation, proportional to the third power of the number of nonterminal symbols and of the input string length. Hence, due to problems in dealing with extensive text corpora, the SCFG has hardly been applied as a language model for very large vocabulary continuous speech recognition. The proposed phrase‐level dependency SCFG allows a significant reduction of the computational load. In experiments with the EDR corpus, the proposed method proved effective. In experiments with the Mainichi corpus, a large‐scale phrase‐level dependency SCFG was built for a very large vocabulary continuous speech recognition system. Speech recognition tests with a vocabulary of about 5000 words showed that the proposed method could not compare with the trigram model in performance; however, when it was used in combination with a trigram model, the error rate was reduced by 14% compared to the trigram model alone. © 2002 Wiley Periodicals, Inc. Syst Comp Jpn, 33(13): 48–59, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.1172

This paper presents the results of a study on modeling the highly inflective Slovenian language. We focus on creating a language model for a large vocabulary speech recognition system. A new data-driven method is proposed for the induction of inflectional morphology into language modeling. The research focus is on data sparsity, which results from the complex morphology of the language. The idea of using subword units is examined. An attempt is made to figure out the segmentation of words into two subword units: stems and endings. No prior knowledge of the language is used. The subword units should fit into the frameworks of the probabilistic language models. A morphologically correct decomposition of words is not being sought, but searching for a decomposition which yields the minimum entropy of the training corpus. This entropy is approximated by using N-gram models. Despite some seemingly over-simplified assumption, the subword models improve the applicability of the language models for a sparse training corpus. The experiments were performed using the VEČER newswire text corpus as a training corpus. The test set was taken from the SNABI speech database, because the final models were evaluated in speech recognition experiments on SNABI speech database. Two different subword-based models are proposed and examined experimentally. The experiments demonstrate that subword-based models, which considerably reduce OOV rate, improve speech recognition WER when compared with standard word-based models, even though they increase test set perplexity. Subword-based models with improved perplexity, but which reduce the OOV rate much less than the previous ones, do not improve speech recognition results.

Japanese large-vocabulary continuous-speech recognition using a newspaper corpus and broadcast news

Phonemes and allophones are the basic speech units for acoustic modeling in the majority of contemporary HMM based speech recognizers. Grapheme-based acoustic sub-word units were applied to multi-lingual and cross-lingual acoustic modeling in many tasks. Grapheme and phoneme based mono-, cross- and bilingual speech recognition of Czech and Slovak in the small and medium vocabulary task has been studied in our previous work. In this article we compare grapheme and phoneme based approach to acoustic modeling and model unit selection in large vocabulary continuous speech recognition (LVCSR) task in Slovak. The main goal of our experimental work is to investigate a possibility to select an optimal set of sub-word units for Slovak LVCSR system.

This work extends and improves a recently introduced (Dec. 2007) dynamic Bayesian network (DBN) based audio-visual automatic speech recognition (AV-ASR) system. That system models the audio and visual components of speech as being composed of the same sub-word units when, in fact, this is not psycholinguistically true. We extend the system to model the audio and visual streams as being composed of separate, yet related, sub-word units. We also introduce a novel stream weighting structure incorporated into the model itself. In doing so, our system makes improvements in word error rate (WER) and overall recognition accuracy in a large vocabulary continuous speech recognition task (LVCSR). The ldquobestrdquo performing proposed system attains a WER of 66.71%whereas the ldquobestrdquo baseline system performs at a WER of 64.30%. The proposed system also improves accuracy to 45.95% from 39.40%.

Subspace Gaussian mixture based language modeling for large vocabulary continuous speech recognition

This paper describes a reading quality scoring system based on large vocabulary continuous speech recognition (LVCSR). Our previous scoring system was based on forced alignment. A disadvantage of forced alignment based system is it can hardly catch huge kinds of reading miscues, while LVCSR based system avoids this disadvantage. The most challenge was that the LVCSR recognition rate was low on our corpus. To improve the recognition rate, we optimized our LVCSR engine for passage scoring tasks by presenting a novel dynamic language model (LM) constructing algorithm. The optimized LVCSR's recognition rate on test speech data was 70.2%, while the recognition rate of the original LVCSR on the same database was 37.9%. Our scoring method was to align the text reference and the confusion network generated from the LVCSR decoding result. The LVCSR based system reduced the scoring error rate of the baseline system by 14.5% relatively.

An improved two-stage mixed language model approach for handling out-of-vocabulary words in large vocabulary continuous speech recognition

This paper presents recent progress in developing speech-totext (STT) and keyword spotting (KWS) systems for the 2014 IARPA-Babel evaluation. Systems have been developed for the limited language pack condition for four of the five development languages in this program phase: Assamese, Bengali, Haitian Creole and Zulu. The systems have several novel characteristics that support rapid development of KWS systems. On the STT side different acoustic units are explored based on phonemic or graphemic representations, and system combination is used to improve STT performance. The acoustic models are trained on only 10 hours of speech data with manual transcriptions, completed with unsupervised training on additional untranscribed data. Both word and subword units (morphologically decomposed, syllables, phonemes) are used for KWS. The KWS systems are based on the multi-hypotheses produced by a consensus network decoding or searching word lattices. The word error rates of the individual STT systems are on the order of 50-60%, and the KWS systems obtain Maximum Term Weighted Values ranging from 30-45% for all keywords (invocabulary and out-of-vocabulary (OOV)). Sub-word units are shown to be successful at locating some of the OOV keywords, and system combination improves system performance. Index Terms: STT, KWS, semi-supervised training, lattice, consensus network, sub-word lexical units, Morfessor

The diachronic nature of broadcast news data leads to the problem of out-of-vocabulary (OOV) words in large vocabulary continuous speech recognition (LVCSR) systems. Analysis of OOV words reveals that a majority of them are proper names (PNs). However, PNs are important for automatic indexing of audio–video content and for obtaining reliable automatic transcriptions. In this paper, we focus on the problem of OOV PNs in diachronic audio documents. To enable the recovery of the PNs missed by the LVCSR system, relevant OOV PNs are retrieved by exploiting the semantic context of the LVCSR transcriptions. For retrieval of OOV PNs, we explore topic and semantic context derived from latent Dirichlet allocation (LDA) topic models, continuous word vector representations and the neural bag-of-words (NBOW) model which is capable of learning task specific word and context representations. We propose a neural bag-of-weighted words (NBOW2) model which learns to assign higher weights to words that are important for retrieval of an OOV PN. With experiments on French broadcast news videos, we show that the NBOW and NBOW2 models outperform the methods based on raw embeddings from LDA and Skip-gram models. Combining the NBOW and NBOW2 models gives a faster convergence during training. Second pass speech recognition experiments, in which the LVCSR vocabulary and language model are updated with the retrieved OOV PNs, demonstrate the effectiveness of the proposed context models.

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h tasks. In particular, we report the state-of-the-art word error rates (WER) of 3.54% on the dev-clean and 3.82% on the test-clean evaluation subsets of LibriSpeech. We introduce a new pretraining scheme by starting with a high time reduction factor and lowering it during training, which is crucial both for convergence and final performance. In some experiments, we also use an auxiliary CTC loss function to help the convergence. In addition, we train long short-term memory (LSTM) language models on subword units. By shallow fusion, we report up to 27% relative improvements in WER over the attention baseline without a language model.

—This paper presents the main improvements brought recently to the SpeeD automatic speech recognition system. Several aspects, such as speech and text resources acquisition, noise-robust speech features and feature transforms are discussed. All the updates in our ASR system are accompanied by experimental results illustrating significant improvements: between 30% and 35% relative WER reductions for various case studies (read/spontaneous speech, noisy/clean speech). In the last part of the paper, our ASR system is also compared with Google’s ASR system and a brief analysis of the results is presented. Keywords -ASR; LVCSR; noise-robust speech recognition; PNCC; LDA. I. I NTRODUCTION Large vocabulary continuous speech recognition (LVCSR) is still an unsolved topic for many languages. The reasons for this are (i) there is a lack of acoustic and linguistic resources needed for development (it is the case of so-called under-resourced languages) and (ii) the scientific research community is not stimulated by any national or international evaluation campaigns (as opposed to languages such as English, French or Chinese). The Romanian language is affected by both the aforementioned problems. In this context, the development of speech and language resources for automatic speech recognition (ASR) is a critical issue that must be addressed to push forward the research in this direction and create LVCSR systems comparable to those available for other languages. This is one of the main goals of the Speech and Dialogue (SpeeD) research group

We like to conversate with other people using both sounds and visuals, as our perception of speech is bimodal. Essentially echoing the same speech structure, we manage to integrate the two modalities and often understand the message better than with the eyes closed. In this work we would like to learn more about the visual nature of speech, coined lip-reading, and to make use of it towards better automatic speech recognition systems. Recent developments in the Machine Learning area, together with the release of suitable audio-visual datasets aimed at large vocabulary continuous speech recognition, have led to a renewal of the lip-reading topic, and allow us to address the recurring question of how to better integrate visual and acoustic speech.

This paper reports the development of a multi-genre Urdu Broadcast (BC) corpus and a Large Vocabulary Continuous Speech Recognition (LVCSR) system. BC speech corpus of 98 hours from 453 speakers is collected and annotated. For acoustic modeling, Time-delay Neural Network (TDNN) is developed with prior Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) training and alignments. For the language model, 3-gram, 4-gram and Recurrent Neural Network (RNN) based models are developed on a text corpus of 188 million words. The developed models are tested on 4.3 hours of unseen BC multi-genre speech dataset and the best Word Error Rate (WER) 18.59% is achieved using RNN based Language Model (LM). Moreover, a detailed word error analysis is carried out to compare the errors made by humans and the Automatic Speech Recognition (ASR) System. The results showed a similar behavior of word misrecognitions by both humans and ASR.