The word error rate (WER) of an automatic speech recognition (ASR) system increases when a mismatch occurs between the training and the testing conditions due to the noise, etc. In this case, the acoustic information can be less reliable. This work aims to improve ASR by modeling long-term semantic relations to compensate for distorted acoustic features. We propose to perform this through rescoring of the ASR N-best hypotheses list. To achieve this, we train a deep neural network (DNN). Our DNN rescoring model is aimed at selecting hypotheses that have better semantic consistency and therefore lower WER. We investigate two types of representations as part of input features to our DNN model: static word embeddings (from word2vec) and dynamic contextual embeddings (from BERT). Acoustic and linguistic features are also included. We perform experiments on the publicly available dataset TED-LIUM mixed with real noise. The proposed rescoring approaches give significant improvement of the WER over the ASR system without rescoring models in two noisy conditions and with n-gram and RNNLM.
Fraunhofer IAIS（弗劳恩霍夫智能分析与信息系统研究所）；University of Bonn（波恩大学）
With the evolution of neural network based methods, automatic speech recognition (ASR) field has been advanced to a level where building an application with speech interface is a reality. In spite of these advances, building a real-time speech recogniser faces several problems such as low recognition accuracy, domain constraint, and out-of-vocabulary words. The low recognition accuracy problem is addressed by improving the acoustic model, language model, decoder and by rescoring the N-best list at the output of the decoder. We are considering the N-best list rescoring approach to improve the r…
The Johns Hopkins University（约翰斯·霍普金斯大学）；Xiaomi Corp.（小米公司）
This paper proposes a parallel computation strategy and a posterior-based lattice expansion algorithm for efficient lattice rescoring with neural language models (LMs) for automatic speech recognition. First, lattices from first-pass decoding are expanded by the proposed posterior-based lattice expansion algorithm. Second, each expanded lattice is converted into a minimal list of hypotheses that covers every arc. Each hypothesis is constrained to be the best path for at least one arc it includes. For each lattice, the neural LM scores of the minimal list are computed in parallel and are then i…
Lattices form a compact representation of multiple hypotheses generated from an automatic speech recognition system and have been shown to improve performance of downstream tasks like spoken language understanding and speech translation, compared to using one-best hypothesis. In this work, we look into the effectiveness of lattice cues for rescoring n-best lists in second-pass. We encode lattices with a recurrent network and train an attention encoder-decoder model for n-best rescoring. The rescoring model with attention to lattices achieves 4-5% relative word error rate reduction over first-p…
Graduate School of Informatics, Kyoto University（京都大学信息学研究生院）
In automatic speech recognition (ASR) rescoring, the hypothesis with the fewest errors should be selected from the n-best list using a language model (LM). However, LMs are usually trained to maximize the likelihood of correct word sequences, not to detect ASR errors. We propose an ASR rescoring method for directly detecting errors with ELECTRA, which is originally a pre-training method for NLP tasks. ELECTRA is pre-trained to predict whether each word is replaced by BERT or not, which can simulate ASR error detection on large text corpora. To make this pre-training closer to ASR error detecti…
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 …
The Hong Kong University of Science and Technology（香港科技大学）；WeBank Co., Ltd（微众银行）；Tsinghua University（清华大学）
Modern Automatic Speech Recognition (ASR) systems primarily rely on scores from an Acoustic Model (AM) and a Language Model (LM) to rescore the N-best lists. With the abundance of recent natural language processing advances, the information utilized by current ASR for evaluating the linguistic and semantic legitimacy of the N-best hypotheses is rather limited. In this paper, we propose a novel Learning-to-Rescore (L2RS) mechanism, which is specialized for utilizing a wide range of textual information from the state-of-the-art NLP models and automatically deciding their weights to rescore the N…
End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these models typically require more data to achieve comparable results. Well-known model adaptation techniques, to account for domain and style adaptation, are not easily applicable to end-to-end systems. Conventional HMM-based systems, on the other hand, have been optimized for various production environments and use cases. In this work, we propose to combine the …
Improved Contextual Recognition In Automatic Speech Recognition Systems By Semantic Lattice Rescoring
Purdue University（普渡大学）；Carnegie Mellon University（卡内基梅隆大学）；University of California Los Angeles（加州大学洛杉矶分校）；McGill University（麦吉尔大学）；Stanford University（斯坦福大学）；Amazon AI（亚马逊人工智能）
本文提出结合 HMM-GMM、DNN 与 transformer 的语义词格重评分框架，以增强 ASR 的上下文识别并降低 WER，且在 LibriSpeech 上验证有效。
In automatic speech recognition, many studies have shown performance improvements using language models (LMs). Recent studies have tried to use bidirectional LMs (biLMs) instead of conventional unidirectional LMs (uniLMs) for rescoring the $N$-best list decoded from the acoustic model. In spite of their theoretical benefits, the biLMs have not given notable improvements compared to the uniLMs in their experiments. This is because their biLMs do not consider the interaction between the two directions. In this paper, we propose a novel sentence scoring method considering the interaction between …
The streaming automatic speech recognition (ASR) models are more popular and suitable for voice-based applications. However, non-streaming models provide better performance as they look at the entire audio context. To leverage the benefits of the non-streaming model in streaming applications like voice search, it is commonly used in second pass re-scoring mode. The candidate hypothesis generated using steaming models is re-scored using a non-streaming model. In this work, we evaluate the non-streaming attention-based end-to-end ASR models on the Flipkart voice search task in both standalone an…
This paper presents the contribution to the third 'CHiME' speech separation and recognition challenge including both front-end signal processing and back-end speech recognition. In the front-end, Multi-channel Wiener filter (MWF) is designed to achieve background noise reduction. Different from traditional MWF, optimized parameter for the tradeoff between noise reduction and target signal distortion is built according to the desired noise reduction level. In the back-end, several techniques are taken advantage to improve the noisy Automatic Speech Recognition (ASR) performance including Deep N…
In automatic speech recognition (ASR), recurrent neural language models (RNNLM) are typically used to refine hypotheses in the form of lattices or n-best lists, which are generated by a beam search decoder with a weaker language model. The RNNLMs are usually trained generatively using the perplexity (PPL) criterion on large corpora of grammatically correct text. However, the hypotheses are noisy, and the RNNLM doesn't always make the choices that minimise the metric we optimise for, the word error rate (WER). To address this mismatch we propose to use a task specific loss to train an RNNLM to …
In this work, we propose a novel and efficient minimum word error rate (MWER) training method for RNN-Transducer (RNN-T). Unlike previous work on this topic, which performs on-the-fly limited-size beam-search decoding and generates alignment scores for expected edit-distance computation, in our proposed method, we re-calculate and sum scores of all the possible alignments for each hypothesis in N-best lists. The hypothesis probability scores and back-propagated gradients are calculated efficiently using the forward-backward algorithm. Moreover, the proposed method allows us to decouple the dec…
Federated Heterogeneous Language Model Optimization for Hybrid Automatic Speech Recognition
Hong Kong Polytechnic University（香港理工大学）；Ant Group（蚂蚁集团）；Shanghai Jiao Tong University（上海交通大学）；Hong Kong University of Science and Technology（香港科学与技术大学）；Shenzhen University（深圳大学）
Google, Inc.（谷歌公司）；University of Washington（华盛顿大学）
The paper revives an older approach to acoustic modeling that borrows from n-gram language modeling in an attempt to scale up both the amount of training data and model size (as measured by the number of parameters in the model), to approximately 100 times larger than current sizes used in automatic speech recognition. In such a data-rich setting, we can expand the phonetic context significantly beyond triphones, as well as increase the number of Gaussian mixture components for the context-dependent states that allow it. We have experimented with contexts that span seven or more context-indepe…
In spoken language understanding (SLU), what the user says is converted to his/her intent. Recent work on end-to-end SLU has shown that accuracy can be improved via pre-training approaches. We revisit ideas presented by Lugosch et al. using speech pre-training and three-module modeling; however, to ease construction of the end-to-end SLU model, we use as our phoneme module an open-source acoustic-phonetic model from a DNN-HMM hybrid automatic speech recognition (ASR) system instead of training one from scratch. Hence we fine-tune on speech only for the word module, and we apply multi-target le…
End-to-end (E2E) models have made rapid progress in automatic speech recognition (ASR) and perform competitively relative to conventional models. To further improve the quality, a two-pass model has been proposed to rescore streamed hypotheses using the non-streaming Listen, Attend and Spell (LAS) model while maintaining a reasonable latency. The model attends to acoustics to rescore hypotheses, as opposed to a class of neural correction models that use only first-pass text hypotheses. In this work, we propose to attend to both acoustics and first-pass hypotheses using a deliberation network. …
Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language model component of the end-to-end model is only trained on transcribed audio-text pairs, which leads to performance degradation especially on rare words. While there have been a variety of work that look at incorporating an external LM trained on text-only data into the end-to-end framework, none of them have taken into account the characteristic error distrib…
Deep neural networks (DNNs) based automatic speech recognition (ASR) systems are often designed using expert knowledge and empirical evaluation. In this paper, a range of neural architecture search (NAS) techniques are used to automatically learn two types of hyper-parameters of state-of-the-art factored time delay neural networks (TDNNs): i) the left and right splicing context offsets; and ii) the dimensionality of the bottleneck linear projection at each hidden layer. These include the DARTS method integrating architecture selection with lattice-free MMI (LF-MMI) TDNN training; Gumbel-Softma…
Carl von Ossietzky Universität Oldenburg（卡尔·冯·奥西茨基奥尔登堡大学）
This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these probabilities. This model does not require the clean speech reference nor the word labels during testing as the ASR decoding step, which finds the most likely sequence of words given phoneme posterior probabilities, is omitted. The model is evaluated via the root-mean-squared error between the predicted and observed speech reception thresholds from eight normal-hear…
Tsinghua University（清华大学）；State Grid Customer Service Center（国家电网客户服务中心）；China Electric Power Research Institute（中国电力科学研究院）
There has been a long recognition that discrete features (n-gram features) and neural network based features have complementary strengths for language models (LMs). Improved performance can be obtained by model interpolation, which is, however, a suboptimal two-step integration of discrete and neural features. The trans-dimensional random field (TRF) framework has the potential advantage of being able to flexibly integrate a richer set of features. However, either discrete or neural features are used alone in previous TRF LMs. This paper develops a mixed-feature TRF LM and demonstrates its adv…
Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model. To further improve ASR performance and facilitate various production requirements, in this paper, we present WeNet 2.0 with four important updates. (1) We propose U2++, a unified two-pass framework with bidirectional attention decoders, which includes the future contextual information by a right-to-left attention decoder to improve the representative …
Trans-dimensional random field language models (TRF LMs) have recently been introduced, where sentences are modeled as a collection of random fields. The TRF approach has been shown to have the advantages of being computationally more efficient in inference than LSTM LMs with close performance and being able to flexibly integrating rich features. In this paper we propose neural TRFs, beyond of the previous discrete TRFs that only use linear potentials with discrete features. The idea is to use nonlinear potentials with continuous features, implemented by neural networks (NNs), in the TRF frame…
National Taiwan Normal University（国立台湾师范大学）；Chunghwa Telecom Laboratories（中华电信研究所）
Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context information with a recurrent neural network or long short-term memory language model (LM) may suffer from the recent bias while excluding the long-range context. In order to capture the long-term semantic interactions among words and across utterances, we put forward disparate conversation history fusion methods for language modeling in automatic speech recognit…
In this work, we propose a classifier for distinguishing device-directed queries from background speech in the context of interactions with voice assistants. Applications include rejection of false wake-ups or unintended interactions as well as enabling wake-word free follow-up queries. Consider the example interaction: $"Computer,~play~music", "Computer,~reduce~the~volume"$. In this interaction, the user needs to repeat the wake-word ($Computer$) for the second query. To allow for more natural interactions, the device could immediately re-enter listening state after the first query (without w…
HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
Nanyang Technological University（南洋理工大学）；Georgia Institute of Technology（佐治亚理工学院）；Norwegian University of Science and Technology（挪威科技大学）；IBM Research AI（IBM人工智能研究院）
National Institute of Informatics（国立信息学研究所）；SOKENDAI (The Graduate University for Advanced Studies)（综合研究大学院大学）；Centre for Speech Technology Research, University of Edinburgh（爱丁堡大学语音技术研究中心）
Neural sequence-to-sequence text-to-speech synthesis (TTS) can produce high-quality speech directly from text or simple linguistic features such as phonemes. Unlike traditional pipeline TTS, the neural sequence-to-sequence TTS does not require manually annotated and complicated linguistic features such as part-of-speech tags and syntactic structures for system training. However, it must be carefully designed and well optimized so that it can implicitly extract useful linguistic features from the input features. In this paper we investigate under what conditions the neural sequence-to-sequence …
