Construction and evaluation of language models based on stochastic context‐free grammar for speech recognition

In large vocabulary continuous speech recognition (LVCSR) for agglutinative and inflectional languages, we encounter problems due to theoretically infinite full-word lexicon size. Sub-word lexicon units may be utilized to dramatically reduce the out-of-vocabulary rate in test data. One can develop language models based on sub-word units to perform LVCSR. However, it has not always been beneficial to use sub-word lexicon units, since shorter units have higher acoustic confusability among them and language model history is effectively shorter as compared to the history in full-word language models. To reduce the aforementioned problems, we propose using the longest possible sub-word units in our lexicon, namely half-words and full-words only. We also incorporate linguistic rules of half-word combination into our statistical language model. The language constraints are represented with a rule-based WFSM which can be combined with an N-gram language model to yield a better and smaller language model. We study the performance of the proposed system for Turkish LVCSR, when the language constraint takes the form of enforcing vowel harmony between stems and endings. We also introduce novel error-rate metrics that are more appropriate than word-error-rate for agglutinative languages. Using half-words with a bi-gram model yields a significant reduction in word-error-rate as compared to a bi-gram full-word model. In addition, combining a tri-gram half-word language model with the vowel-harmony WFSM improves the accuracy further when rescoring the bi-gram lattices.

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

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.

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

—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

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

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.

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.

This paper proposes an improved probabilistic CFG (Context-Free Grammar), called the mixture probabilistic CFG, based on an idea of cluster-based language modeling. This model assumes that the language model parameters have different probability distributions in different topics or domains. In order to performs topic-or domaindependent language modeling, we first divide the training corpus into a number of subcorpora according to their topics or domains, and then estimate separate probability distribution from each subcorpus. Therefore, a mixture probabilistic CFG has several different probability distributions for CFG productuions. The language model probability of a sentence is calculated as the mixture of these probability distributions. The mixture probabilistic CFG enables us to make a context-or topic-dependent language model, and thus accurate language modeling would be possible. The proposed model was evaluated by calculating test-set perplexity using the ADD (ATR Dialogue Database) corpus and a Japanese intra-phrase grammar. The mixture probabilistic CFG had a test-set perplexity of 2.47/phone, while simple probabilistic CFG had a test-set perplexity of 2.77/phone. We also conducted speech recognition experiments using three language models, including pure CFG (without probabilities), simple probabilistic CFG, and the mixture probabilistic CFG. In our experiments, the mixture probabilistic CFG attained the best performance. The proposed model was also evaluated using sentence-level clustering. This evaluation used the dialogue corpus in which each utterance is annotated with an utterance type called IFT (Illocutionary Force Type). Using these IFTs, we divided the corpus into 9 clusters, and then estimated production probabilities from these clusters. Without IFT clustering, the perplexity was 2.18 per phone, but using IFT clustering, the perplexity was reduced to 1.82 per phone.

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

Voice search is the technology that enables users to access information using spoken queries. Automatic speech recognizer (ASR) is one of the key modules for voice search systems. However, the high error rate of the state-of-the-art large vocabulary continuous speech recognition (LVCSR) is the bottleneck for most voice search systems. In this paper, we first build a baseline system using language model (LM) with domain-specific information. To improve our system, we propose a forward-backward LVCSR system combination method to decrease the search errors in speech recognition. This also helps to improve the spoken language understanding (SLU) performance. Experiment results show that our proposed method improves the performance of speech recognition by 5.7% relative CER reduction and increases the F1-measure of SLU by 1.5% absolute on our test set.KeywordsVoice searchLVCSRSLUforward-backwardsystem combination

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.

We describe a corpus-based induction algorithm for probabilistic context-free grammars. The algorithm employs a greedy heuristic search within a Bayesian framework, and a post-pass using the Inside-Outside algorithm. We compare the performance of our algorithm to n-gram models and the Inside-Outside algorithm in three language modeling tasks. In two of the tasks, the training data is generated by a probabilistic context-free grammar and in both tasks our algorithm outperforms the other techniques. The third task involves naturally-occurring data, and in this task our algorithm does not perform as well as n-gram models but vastly outperforms the Inside-Outside algorithm.

This article introduces a novel approach to model morphosyntax in morpheme unit based speech recognizers. The proposed method is evaluated in our recent Hungarian large vocabulary continuous speech recognition (LVCSR) system. The architecture of the recognition system is based on the weighted finite state transducer (WFST) paradigm. The task domain is the recognition of fluently read sentences selected from a major daily newspaper. The vocabulary units used in the system are morpheme based in order to provide sufficient coverage of the large number of word-forms resulting from affixation and compounding. Besides the standard morpheme N-gram language model we evaluate the novel stochastic morphosyntactic language model (SMLM) that describes the valid word-forms (morpheme combinations) of the language. Thanks to the flexible transducer-based architecture of the system the morphosyntactic component is integrated seamlessly with the basic modules with no need to modify the decoder itself. The proposed stochastic morphosyntactic language model decreases the error rate by 17.9% relatively compared to the baseline trigram system. The morpheme error rate of the best configuration is 14.75% in a 1350 morpheme Hungarian dictation task.

The Tigrinya language is agglutinative and has a large number of inflected and derived forms of words. Therefore a Tigrinya large vocabulary continuous speech recognition system often has a large number of different units and a high out-of-vocabulary (OOV) rate if a word is used as a recognition unit of a language model (LM) and lexicon. Therefore a morpheme-based approach has often been used and a morpheme is used as the recognition unit to reduce the high OOV rate. This paper presents an automatic speech recognition experiment conducted to see the effect of OOV words on the performance speech recognition system for Tigrinya. We tried to solve the OOV problem by using morphemes as lexicon and language model units. It has been found that the morpheme-based recognition system is better lexical and language modeling units than words. An absolute improvement (in word recognition accuracy) of 3.45 token and 8.36 types has been obtained as a result of using a morph-based vocabulary.