Multilingual self-supervised speech representation models have greatly enhanced the speech recognition performance for low-resource languages, and the compression of these huge models has also become a crucial prerequisite for their industrial application. In this paper, we propose DistilXLSR, a distilled cross-lingual speech representation model. By randomly shuffling the phonemes of existing speech, we reduce the linguistic information and distill cross-lingual models using only English data. We also design a layer-jumping initialization method to fully leverage the teacher's pre-trained weights. Experiments on 2 kinds of teacher models and 15 low-resource languages show that our method can reduce the parameters by 50% while maintaining cross-lingual representation ability. Our method is proven to be generalizable to various languages/teacher models and has the potential to improve the cross-lingual performance of the English pre-trained models.
End-to-end speech summarization (E2E SSum) directly summarizes input speech into easy-to-read short sentences with a single model. This approach is promising because it, in contrast to the conventional cascade approach, can utilize full acoustical information and mitigate to the propagation of transcription errors. However, due to the high cost of collecting speech-summary pairs, an E2E SSum model tends to suffer from training data scarcity and output unnatural sentences. To overcome this drawback, we propose for the first time to integrate a pre-trained language model (LM), which is highly capable of generating natural sentences, into the E2E SSum decoder via transfer learning. In addition, to reduce the gap between the independently pre-trained encoder and decoder, we also propose to transfer the baseline E2E SSum encoder instead of the commonly used automatic speech recognition encoder. Experimental results show that the proposed model outperforms baseline and data augmented models.
Domain adaptation using text-only corpus is challenging in end-to-end(E2E) speech recognition. Adaptation by synthesizing audio from text through TTS is resource-consuming. We present a method to learn Unified Speech-Text Representation in Conformer Transducer(USTR-CT) to enable fast domain adaptation using the text-only corpus. Different from the previous textogram method, an extra text encoder is introduced in our work to learn text representation and is removed during inference, so there is no modification for online deployment. To improve the efficiency of adaptation, single-step and multi-step adaptations are also explored. The experiments on adapting LibriSpeech to SPGISpeech show the proposed method reduces the word error rate(WER) by relatively 44% on the target domain, which is better than those of TTS method and textogram method. Also, it is shown the proposed method can be combined with internal language model estimation(ILME) to further improve the performance.
Despite the impressive performance recently achieved by automatic speech recognition (ASR), we observe two primary challenges that hinder its broader applications: (1) The difficulty of introducing scalability into the model to support more languages with limited training, inference, and storage overhead; (2) The low-resource adaptation ability that enables effective low-resource adaptation while avoiding over-fitting and catastrophic forgetting issues. Inspired by recent findings, we hypothesize that we can address the above challenges with modules widely shared across languages. To this end, we propose an ASR framework, dubbed \METHODNS, that, \textit{for the first time}, simultaneously achieves strong multilingual scalability and low-resource adaptation ability thanks to its modularize-then-assemble strategy. Specifically, \METHOD learns a small set of generalizable sub-modules and adaptively assembles them for different languages to reduce the multilingual overhead and enable effective knowledge transfer for low-resource adaptation. Extensive experiments and visualizations demonstrate that \METHOD can effectively discover language similarity and improve multilingual and low-resource ASR performance over state-of-the-art (SOTA) methods, e.g., under multilingual-ASR, our framework achieves a 0.13$\sim$2.41 lower character error rate (CER) with 30\% smaller inference overhead over SOTA solutions on multilingual ASR and a comparable CER, with nearly 50 times fewer trainable parameters over SOTA solutions on low-resource tuning, respectively.
Audio-visual speech recognition (AVSR) gains increasing attention from researchers as an important part of human-computer interaction. However, the existing available Mandarin audio-visual datasets are limited and lack the depth information. To address this issue, this work establishes the MAVD, a new large-scale Mandarin multimodal corpus comprising 12,484 utterances spoken by 64 native Chinese speakers. To ensure the dataset covers diverse real-world scenarios, a pipeline for cleaning and filtering the raw text material has been developed to create a well-balanced reading material. In particular, the latest data acquisition device of Microsoft, Azure Kinect is used to capture depth information in addition to the traditional audio signals and RGB images during data acquisition. We also provide a baseline experiment, which could be used to evaluate the effectiveness of the dataset. The dataset and code will be released at https://github.com/SpringHuo/MAVD.
The recent emergence of joint CTC-Attention model shows significant improvement in automatic speech recognition (ASR). The improvement largely lies in the modeling of linguistic information by decoder. The decoder joint-optimized with an acoustic encoder renders the language model from ground-truth sequences in an auto-regressive manner during training. However, the training corpus of the decoder is limited to the speech transcriptions, which is far less than the corpus needed to train an acceptable language model. This leads to poor robustness of decoder. To alleviate this problem, we propose linguistic-enhanced transformer, which introduces refined CTC information to decoder during training process, so that the decoder can be more robust. Our experiments on AISHELL-1 speech corpus show that the character error rate (CER) is relatively reduced by up to 7%. We also find that in joint CTC-Attention ASR model, decoder is more sensitive to linguistic information than acoustic information.
Connectionist Temporal Classification (CTC) is a widely used criterion for training supervised sequence-to-sequence (seq2seq) models. It enables learning the relations between input and output sequences, termed alignments, by marginalizing over perfect alignments (that yield the ground truth), at the expense of imperfect alignments. This binary differentiation of perfect and imperfect alignments falls short of capturing other essential alignment properties that hold significance in other real-world applications. Here we propose $\textit{Align With Purpose}$, a $\textbf{general Plug-and-Play framework}$ for enhancing a desired property in models trained with the CTC criterion. We do that by complementing the CTC with an additional loss term that prioritizes alignments according to a desired property. Our method does not require any intervention in the CTC loss function, enables easy optimization of a variety of properties, and allows differentiation between both perfect and imperfect alignments. We apply our framework in the domain of Automatic Speech Recognition (ASR) and show its generality in terms of property selection, architectural choice, and scale of training dataset (up to 280,000 hours). To demonstrate the effectiveness of our framework, we apply it to two unrelated properties: emission time and word error rate (WER). For the former, we report an improvement of up to 570ms in latency optimization with a minor reduction in WER, and for the latter, we report a relative improvement of 4.5% WER over the baseline models. To the best of our knowledge, these applications have never been demonstrated to work on a scale of data as large as ours. Notably, our method can be implemented using only a few lines of code, and can be extended to other alignment-free loss functions and to domains other than ASR.
Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial use of strong visual representations, e.g. by finetuning pretrained image recognition networks, significantly less attention has been paid to its counterpart: the speech component. In this work, we investigate ways of improving the base speech recognition system by following similar techniques to the ones used for the visual encoder, namely, transferring representations and data augmentation. First, we show that starting from a pretrained ASR significantly improves the state-of-the-art performance; remarkably, even when building upon a strong unimodal system, we still find gains by including the visual modality. Second, we employ speech data augmentation techniques to encourage the multimodal system to attend to the visual stimuli. This technique replaces previously used word masking and comes with the benefits of being conceptually simpler and yielding consistent improvements in the multimodal setting. We provide empirical results on three multimodal datasets, including the newly introduced Localized Narratives.
Hypernasality is an abnormal resonance in human speech production, especially in patients with craniofacial anomalies such as cleft palate. In clinical application, hypernasality estimation is crucial in cleft palate diagnosis, as its results determine the subsequent surgery and additional speech therapy. Therefore, designing an automatic hypernasality assessment method will facilitate speech-language pathologists to make precise diagnoses. Existing methods for hypernasality estimation only conduct acoustic analysis based on low-resource cleft palate dataset, by using statistical or neural network-based features. In this paper, we propose a novel approach that uses automatic speech recognition model to improve hypernasality estimation. Specifically, we first pre-train an encoder-decoder framework in an automatic speech recognition (ASR) objective by using speech-to-text dataset, and then fine-tune ASR encoder on the cleft palate dataset for hypernasality estimation. Benefiting from such design, our model for hypernasality estimation can enjoy the advantages of ASR model: 1) compared with low-resource cleft palate dataset, the ASR task usually includes large-scale speech data in the general domain, which enables better model generalization; 2) the text annotations in ASR dataset guide model to extract better acoustic features. Experimental results on two cleft palate datasets demonstrate that our method achieves superior performance compared with previous approaches.
This paper presents techniques and findings for improving the performance of low-resource speech to text translation (ST). We conducted experiments on both simulated and real-low resource setups, on language pairs English - Portuguese, and Tamasheq - French respectively. Using the encoder-decoder framework for ST, our results show that a multilingual automatic speech recognition system acts as a good initialization under low-resource scenarios. Furthermore, using the CTC as an additional objective for translation during training and decoding helps to reorder the internal representations and improves the final translation. Through our experiments, we try to identify various factors (initializations, objectives, and hyper-parameters) that contribute the most for improvements in low-resource setups. With only 300 hours of pre-training data, our model achieved 7.3 BLEU score on Tamasheq - French data, outperforming prior published works from IWSLT 2022 by 1.6 points.