Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e.g. byte-pair encoding (BPE). The mapping from pronunciation to spelling is learned completely from data. In contrast to this, classical approaches to ASR employ secondary knowledge sources in the form of phoneme lists to define phonetic output labels and pronunciation lexica. In this work, we do a systematic comparison between grapheme- and phoneme-based output labels for an encoder-decoder-attention ASR model. We investigate the use of single phonemes as well as BPE-based phoneme groups as output labels of our model. To preserve a simplified and efficient decoder design, we also extend the phoneme set by auxiliary units to be able to distinguish homophones. Experiments performed on the Switchboard 300h and LibriSpeech benchmarks show that phoneme-based modeling is competitive to grapheme-based encoder-decoder-attention modeling.
Budapest University of Technology and Economics（布达佩斯技术与经济大学）
Attention mechanism is one of the most successful techniques in deep learning based Natural Language Processing (NLP). The transformer network architecture is completely based on attention mechanisms, and it outperforms sequence-to-sequence models in neural machine translation without recurrent and convolutional layers. Grapheme-to-phoneme (G2P) conversion is a task of converting letters (grapheme sequence) to their pronunciations (phoneme sequence). It plays a significant role in text-to-speech (TTS) and automatic speech recognition (ASR) systems. In this paper, we investigate the application…
LLM-based phoneme-to-grapheme for phoneme-based speech recognition
Xinjiang University（新疆大学）；Tsinghua University（清华大学）；School of Computer Science and Technology（计算机科学与技术学院）；Guangxi Radio and Television Monitoring Center（广西广播电视监测中心）
The task of grapheme-to-phoneme (G2P) conversion is important for both speech recognition and synthesis. Similar to other speech and language processing tasks, in a scenario where only small-sized training data are available, learning G2P models is challenging. We describe a simple approach of exploiting model ensembles, based on multilingual Transformers and self-training, to develop a highly effective G2P solution for 15 languages. Our models are developed as part of our participation in the SIGMORPHON 2020 Shared Task 1 focused at G2P. Our best models achieve 14.99 word error rate (WER) and…
Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems. Most g2p systems are monolingual: they require language-specific data or handcrafting of rules. Such systems are difficult to extend to low resource languages, for which data and handcrafted rules are not available. As an alternative, we present a neural sequence-to-sequence approach to g2p which is trained on spelling--pronunciation pairs in hundreds of languages. The system shares a single encoder and decoder across all languages, allowing it to utilize the intrinsic similarities be…
As a key component of automated speech recognition (ASR) and the front-end in text-to-speech (TTS), grapheme-to-phoneme (G2P) plays the role of converting letters to their corresponding pronunciations. Existing methods are either slow or poor in performance, and are limited in application scenarios, particularly in the process of on-device inference. In this paper, we integrate the advantages of both expert knowledge and connectionist temporal classification (CTC) based neural network and propose a novel method named LiteG2P which is fast, light and theoretically parallel. With the carefully l…
Grapheme-to-phoneme (G2P) conversion is an important task in automatic speech recognition and text-to-speech systems. Recently, G2P conversion is viewed as a sequence to sequence task and modeled by RNN or CNN based encoder-decoder framework. However, previous works do not consider the practical issues when deploying G2P model in the production system, such as how to leverage additional unlabeled data to boost the accuracy, as well as reduce model size for online deployment. In this work, we propose token-level ensemble distillation for G2P conversion, which can (1) boost the accuracy by disti…
Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech recognition for Indian languages. Our proposed model consists of a Conformer [1] encoder, two parallel transformer decoders, and a language classifier. We use a phoneme decoder (PHN-DEC) for the phoneme recognition task and a grapheme decoder (GRP-DEC) to predict grapheme sequence along with language information. We consider phoneme recognition and language id…
Transformers have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. In this work, we propose a multi-task learning-based transformer model for low-resource multilingual speech recognition for Indian languages. Our proposed model consists of a conformer [1] encoder and two parallel transformer decoders. We use a phoneme decoder (PHN-DEC) for the phoneme recognition task and a grapheme decoder (GRP-DEC) to predict grapheme sequence. We consider the phoneme recognition task as an auxiliary task for our multi-task learning framew…
In conventional speech recognition, phoneme-based models outperform grapheme-based models for non-phonetic languages such as English. The performance gap between the two typically reduces as the amount of training data is increased. In this work, we examine the impact of the choice of modeling unit for attention-based encoder-decoder models. We conduct experiments on the LibriSpeech 100hr, 460hr, and 960hr tasks, using various target units (phoneme, grapheme, and word-piece); across all tasks, we find that grapheme or word-piece models consistently outperform phoneme-based models, even though …
Contextual automatic speech recognition, i.e., biasing recognition towards a given context (e.g. user's playlists, or contacts), is challenging in end-to-end (E2E) models. Such models maintain a limited number of candidates during beam-search decoding, and have been found to recognize rare named entities poorly. The problem is exacerbated when biasing towards proper nouns in foreign languages, e.g., geographic location names, which are virtually unseen in training and are thus out-of-vocabulary (OOV). While grapheme or wordpiece E2E models might have a difficult time spelling OOV words, phonem…
ViSpeechFormer: A Phonemic Approach for Vietnamese Automatic Speech Recognition
Faculty of Information Science and Engineering（信息科学与工程学院）；University of Information Technology（信息技术大学）；Vietnam National University, Ho Chi Minh city（胡志明市越南国家大学）
ViSpeechFormer 是首个基于音素的越南语 ASR 框架，通过建模音素表示实现了更强的性能和更好的泛化能力。
Neural network models have achieved state-of-the-art performance on grapheme-to-phoneme (G2P) conversion. However, their performance relies on large-scale pronunciation dictionaries, which may not be available for a lot of languages. Inspired by the success of the pre-trained language model BERT, this paper proposes a pre-trained grapheme model called grapheme BERT (GBERT), which is built by self-supervised training on a large, language-specific word list with only grapheme information. Furthermore, two approaches are developed to incorporate GBERT into the state-of-the-art Transformer-based G…
Code-Switching refers to the phenomenon of switching languages within a sentence or discourse. However, limited code-switching , different language phoneme-sets and high rebuilding costs throw a challenge to make the specialized acoustic model for code-switching speech recognition. In this paper, we make use of limited code-switching data as driving materials and explore a shortcut to quickly develop intra-sentential code-switching recognition skill on the commissioned native language acoustic model, where we propose a data-driven method to make the seed lexicon which is used to train grapheme…
Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level or sup-phoneme-level and jointly trained with phonemes, making them inefficient for the downstream TTS task where only phonemes are needed. In this work, we propose a phoneme-level BERT (PL-BERT) with a pretext task of predicting the corresponding graphemes along with the regular masked phoneme predictions. Subjective evaluations show that our phoneme-level …
This paper describes the architecture and implementation of a rule-based grapheme to phoneme converter for Turkish. The system accepts surface form as input, outputs SAMPA mapping of the all parallel pronounciations according to the morphological analysis together with stress positions. The system has been implemented in Python
Most Chinese Grapheme-to-Phoneme (G2P) systems employ a three-stage framework that first transforms input sequences into character embeddings, obtains linguistic information using language models, and then predicts the phonemes based on global context about the entire input sequence. However, linguistic knowledge alone is often inadequate. Language models frequently encode overly general structures of a sentence and fail to cover specific cases needed to use phonetic knowledge. Also, a handcrafted post-processing system is needed to address the problems relevant to the tone of the characters. …
Mila - Quebec AI Institute（米拉-魁北克人工智能研究院）；Université de Montréal（蒙特利尔大学）；Concordia University（康考迪亚大学）
End-to-end speech synthesis models directly convert the input characters into an audio representation (e.g., spectrograms). Despite their impressive performance, such models have difficulty disambiguating the pronunciations of identically spelled words. To mitigate this issue, a separate Grapheme-to-Phoneme (G2P) model can be employed to convert the characters into phonemes before synthesizing the audio. This paper proposes SoundChoice, a novel G2P architecture that processes entire sentences rather than operating at the word level. The proposed architecture takes advantage of a weighted homog…
This paper introduces PnG BERT, a new encoder model for neural TTS. This model is augmented from the original BERT model, by taking both phoneme and grapheme representations of text as input, as well as the word-level alignment between them. It can be pre-trained on a large text corpus in a self-supervised manner, and fine-tuned in a TTS task. Experimental results show that a neural TTS model using a pre-trained PnG BERT as its encoder yields more natural prosody and more accurate pronunciation than a baseline model using only phoneme input with no pre-training. Subjective side-by-side prefere…
Grapheme-to-phoneme (G2P) conversion is the process of converting the written form of words to their pronunciations. It has an important role for text-to-speech (TTS) synthesis and automatic speech recognition (ASR) systems. In this paper, we aim to evaluate and enhance the robustness of G2P models. We show that neural G2P models are extremely sensitive to orthographical variations in graphemes like spelling mistakes. To solve this problem, we propose three controlled noise introducing methods to synthesize noisy training data. Moreover, we incorporate the contextual information with the basel…
In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in speech-text joint pre-training comes from the significant difference between speech and text modalities, especially for Mandarin speech and text. Unlike English and other languages with an alphabetic writing system, Mandarin uses an ideographic writing system where character and sound are not tightly mapped to one another. Therefore, we propose to introduce the phonem…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
The choice of modeling units is critical to automatic speech recognition (ASR) tasks. Conventional ASR systems typically choose context-dependent states (CD-states) or context-dependent phonemes (CD-phonemes) as their modeling units. However, it has been challenged by sequence-to-sequence attention-based models, which integrate an acoustic, pronunciation and language model into a single neural network. On English ASR tasks, previous attempts have already shown that the modeling unit of graphemes can outperform that of phonemes by sequence-to-sequence attention-based model. In this paper, we ar…
Automated speech recognition coverage of the world's languages continues to expand. However, standard phoneme based systems require handcrafted lexicons that are difficult and expensive to obtain. To address this problem, we propose a training methodology for a grapheme-based speech recognizer that can be trained in a purely data-driven fashion. Built with LSTM networks and trained with the cross-entropy loss, the grapheme-output acoustic models we study are also extremely practical for real-world applications as they can be decoded with conventional ASR stack components such as language model…
For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-to-end models which seek to combine acoustic, pronunciation, and language model components into a single neural network. Such systems, which typically predict graphemes or words, simplify the recognition process since they remove the need for a separate expert-curated pronunciation lexicon to map from phoneme-based units to words. However, there has been little previous work comparing phoneme-based versus grapheme-ba…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Carnegie Mellon University（卡内基梅隆大学）
Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large training corpora are readily available for languages like English, there exists a long tail of languages which do suffer from a lack of resources. One method to handle data sparsity is to use data from additional source languages and build a multilingual system. Recently, ASR systems based on recurrent neural networks (RNNs) trained with connectionist temporal classification (CTC) have gained substantial research interest. In this work, w…
Keyword spotting (KWS) is an important technique for speech applications, which enables users to activate devices by speaking a keyword phrase. Although a phoneme classifier can be used for KWS, exploiting a large amount of transcribed data for automatic speech recognition (ASR), there is a mismatch between the training criterion (phoneme recognition) and the target task (KWS). Recently, multi-task learning has been applied to KWS to exploit both ASR and KWS training data. In this approach, an output of an acoustic model is split into two branches for the two tasks, one for phoneme transcripti…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
In a multilingual country like India, multilingual Automatic Speech Recognition (ASR) systems have much scope. Multilingual ASR systems exhibit many advantages like scalability, maintainability, and improved performance over the monolingual ASR systems. However, building multilingual systems for Indian languages is challenging since different languages use different scripts for writing. On the other hand, Indian languages share a lot of common sounds. Common Label Set (CLS) exploits this idea and maps graphemes of various languages with similar sounds to common labels. Since Indian languages a…
We demonstrate a network visualization technique to analyze the recurrent state inside the LSTMs/GRUs used commonly in language and acoustic models. Interpreting intermediate state and network activations inside end-to-end models remains an open challenge. Our method allows users to understand exactly how much and what history is encoded inside recurrent state in grapheme sequence models. Our procedure trains multiple decoders that predict prior input history. Compiling results from these decoders, a user can obtain a signature of the recurrent kernel that characterizes its memory behavior. We…
Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Samsung Electronics（三星电子）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural network. In these models, the Transformer, a new sequence-to-sequence attention-based model relying entirely on self-attention without using RNNs or convolutions, achieves a new single-model state-of-the-art BLEU on neural machine translation (NMT) tasks. Since the outstanding performance of the Transformer, we extend it to speech and concentrate on it as the basic architecture of s…
Korea University（高丽大学）；College of Engineering（工学院）
Wav2vec 2.0 is an end-to-end framework of self-supervised learning for speech representation that is successful in automatic speech recognition (ASR), but most of the work on the topic has been developed with a single language: English. Therefore, it is unclear whether the self-supervised framework is effective in recognizing other languages with different writing systems, such as Korean which uses the Hangul having a unique writing system. In this paper, we present K-Wav2Vec 2.0, which is a modified version of Wav2vec 2.0 designed for Korean automatic speech recognition by exploring and optim…
STC-Innovations Ltd（STC创新有限公司）；LIUM, University of Le Mans（勒芒大学LIUM实验室）；ITMO University（圣彼得堡国立信息技术机械与光学大学）
This work proposes a novel approach to out-of-vocabulary (OOV) keyword search (KWS) task. The proposed approach is based on using high-level features from an automatic speech recognition (ASR) system, so called phoneme posterior based (PPB) features, for decoding. These features are obtained by calculating time-dependent phoneme posterior probabilities from word lattices, followed by their smoothing. For the PPB features we developed a special novel very fast, simple and efficient OOV decoder. Experimental results are presented on the Georgian language from the IARPA Babel Program, which was t…
Technische Universität Darmstadt（达姆施塔特工业大学）；German Institute for Educational Research and Educational Information（德国教育研究与教育信息研究所）
We analyze the performance of encoder-decoder neural models and compare them with well-known established methods. The latter represent different classes of traditional approaches that are applied to the monotone sequence-to-sequence tasks OCR post-correction, spelling correction, grapheme-to-phoneme conversion, and lemmatization. Such tasks are of practical relevance for various higher-level research fields including digital humanities, automatic text correction, and speech recognition. We investigate how well generic deep-learning approaches adapt to these tasks, and how they perform in compa…
Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）
End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling, pronunciation lexicon, and language modeling, the end-to-end paradigm is both conceptually simpler and has the potential benefit of training the entire system on the end task. However, such neural network models are more opaque: it is not clear how to interpret the role of different parts of the network and what information it learns during training. In this pape…
Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision
School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；China Unicom (Guangdong) Industrial Internet Co., Ltd（中国联通（广东）工业互联网有限公司）；Tsinghua University（清华大学）
Tsinghua University（清华大学）；Beijing Language and Culture University（北京语言大学）
Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-CRF framework inherits the data-efficiency of the hybrid approach and the simplicity of the end-to-end approach. In this paper, we further advance CTC-CRF based ASR technique with explorations on modeling units and neural architectures. Specifically, we investigate techniques to enable the recently developed wordpiece modeling units and Conformer neural networks to be succesfully applied in CTC-CRFs. Experiments are …
