End-to-end (E2E) modeling is advantageous for automatic speech recognition (ASR) especially for Japanese since word-based tokenization of Japanese is not trivial, and E2E modeling is able to model character sequences directly. This paper focuses on the latest E2E modeling techniques, and investigates their performances on character-based Japanese ASR by conducting comparative experiments. The results are analyzed and discussed in order to understand the relative advantages of long short-term memory (LSTM), and Conformer models in combination with connectionist temporal classification, transducer, and attention-based loss functions. Furthermore, the paper investigates on effectivity of the recent training techniques such as data augmentation (SpecAugment), variational noise injection, and exponential moving average. The best configuration found in the paper achieved the state-of-the-art character error rates of 4.1%, 3.2%, and 3.5% for Corpus of Spontaneous Japanese (CSJ) eval1, eval2, and eval3 tasks, respectively. The system is also shown to be computationally efficient thanks to the efficiency of Conformer transducers.
End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data. However, it is known that domain mismatch between training and testing data often leads to a degradation of recognition accuracy. In this work, we focus on the unsupervised domain adaptation for ASR and propose CMatch, a Character-level distribution matching method to perform fine-grained adaptation between each character in two domains. First, to obtain labels for the features belonging to each character, we achieve frame-level label assignment using the Connectionist Temporal Classification (CTC) pseudo labels. Then, we match the character-level distributions using Maximum Mean Discrepancy. We train our algorithm using the self-training technique. Experiments on the Libri-Adapt dataset show that our proposed approach achieves 14.39% and 16.50% relative Word Error Rate (WER) reduction on both cross-device and cross-environment ASR. We also comprehensively analyze the different strategies for frame-level label assignment and Transformer adaptations.
The quality of a multilingual speech recognition system can be improved by adaptation methods if the input language is specified. For systems that can accept multilingual inputs, the popular approach is to apply a language identifier to the input then switch or configure decoders in the next step, or use one more subsequence model to select the output from a set of candidates. Motivated by the goal of reducing the latency for real-time applications, in this paper, a language model rescoring method is firstly applied to produce all possible candidates for target languages, then a simple score is proposed to automatically select the output without any identifier model or language specification of the input language. The main point is that this score can be simply and automatically estimated on-the-fly so that the whole decoding pipeline is more simple and compact. Experimental results showed that this method can achieve the same quality as when the input language is specified. In addition, we present to design an English and Vietnamese End-to-End model to deal with not only the problem of cross-lingual speakers but also as a solution to improve the accuracy of borrowed words of English in Vietnamese.
We present a new workflow to create components for the MaryTTS text-to-speech synthesis platform, which is popular with researchers and developers, extending it to support new languages and custom synthetic voices. This workflow replaces the previous toolkit with an efficient, flexible process that leverages modern build automation and cloud-hosted infrastructure. Moreover, it is compatible with the updated MaryTTS architecture, enabling new features and state-of-the-art paradigms such as synthesis based on deep neural networks (DNNs). Like MaryTTS itself, the new tools are free, open source software (FOSS), and promote the use of open data.
In this paper, we investigate the use of prediction-adaptation-correction recurrent neural networks (PAC-RNNs) for low-resource speech recognition. A PAC-RNN is comprised of a pair of neural networks in which a {\it correction} network uses auxiliary information given by a {\it prediction} network to help estimate the state probability. The information from the correction network is also used by the prediction network in a recurrent loop. Our model outperforms other state-of-the-art neural networks (DNNs, LSTMs) on IARPA-Babel tasks. Moreover, transfer learning from a language that is similar to the target language can help improve performance further.
We propose a novel pitch estimation technique called DeepF0, which leverages the available annotated data to directly learns from the raw audio in a data-driven manner. F0 estimation is important in various speech processing and music information retrieval applications. Existing deep learning models for pitch estimations have relatively limited learning capabilities due to their shallow receptive field. The proposed model addresses this issue by extending the receptive field of a network by introducing the dilated convolutional blocks into the network. The dilation factor increases the network receptive field exponentially without increasing the parameters of the model exponentially. To make the training process more efficient and faster, DeepF0 is augmented with residual blocks with residual connections. Our empirical evaluation demonstrates that the proposed model outperforms the baselines in terms of raw pitch accuracy and raw chroma accuracy even using 77.4% fewer network parameters. We also show that our model can capture reasonably well pitch estimation even under the various levels of accompaniment noise.
Modern approaches to text to speech require the entire input character sequence to be processed before any audio is synthesised. This latency limits the suitability of such models for time-sensitive tasks like simultaneous interpretation. Interleaving the action of reading a character with that of synthesising audio reduces this latency. However, the order of this sequence of interleaved actions varies across sentences, which raises the question of how the actions should be chosen. We propose a reinforcement learning based framework to train an agent to make this decision. We compare our performance against that of deterministic, rule-based systems. Our results demonstrate that our agent successfully balances the trade-off between the latency of audio generation and the quality of synthesised audio. More broadly, we show that neural sequence-to-sequence models can be adapted to run in an incremental manner.
In this paper, we investigate the benefit that off-the-shelf word embedding can bring to the sequence-to-sequence (seq-to-seq) automatic speech recognition (ASR). We first introduced the word embedding regularization by maximizing the cosine similarity between a transformed decoder feature and the target word embedding. Based on the regularized decoder, we further proposed the fused decoding mechanism. This allows the decoder to consider the semantic consistency during decoding by absorbing the information carried by the transformed decoder feature, which is learned to be close to the target word embedding. Initial results on LibriSpeech demonstrated that pre-trained word embedding can significantly lower ASR recognition error with a negligible cost, and the choice of word embedding algorithms among Skip-gram, CBOW and BERT is important.
Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target sequence. Most attentional mechanisms used today is based on a global attention property which requires a computation of a weighted summarization of the whole input sequence generated by encoder states. However, it is computationally expensive and often produces misalignment on the longer input sequence. Furthermore, it does not fit with monotonous or left-to-right nature in several tasks, such as automatic speech recognition (ASR), grapheme-to-phoneme (G2P), etc. In this paper, we propose a novel attention mechanism that has local and monotonic properties. Various ways to control those properties are also explored. Experimental results on ASR, G2P and machine translation between two languages with similar sentence structures, demonstrate that the proposed encoder-decoder model with local monotonic attention could achieve significant performance improvements and reduce the computational complexity in comparison with the one that used the standard global attention architecture.
Add to Chrome
Add to Firefox