相关论文: Speech Pre-training with Acoustic Piece

Learning meaningful and general representations from unannotated speech that are applicable to a wide range of tasks remains challenging. In this paper we propose to use autoregressive predictive coding (APC), a recently proposed…

Speech segmentation is an essential part of speech translation (ST) systems in real-world scenarios. Since most ST models are designed to process speech segments, long-form audio must be partitioned into shorter segments before translation.…

The massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art…

Self-supervised learning has been used to leverage unlabelled data, improving accuracy and generalisation of speech systems through the training of representation models. While many recent works have sought to produce effective…

Self-supervised pretraining for Automated Speech Recognition (ASR) has shown varied degrees of success. In this paper, we propose to jointly learn representations during pretraining from two different modalities: speech and text. The…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

Speech recognition technologies are gaining enormous popularity in various industrial applications. However, building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To…

The goal of our research is to automatically retrieve the satisfaction and the frustration in real-life call-center conversations. This study focuses an industrial application in which the customer satisfaction is continuously tracked down…

Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the…

The scarcity of labeled audio-visual datasets is a constraint for training superior audio-visual speaker diarization systems. To improve the performance of audio-visual speaker diarization, we leverage pre-trained supervised and…

Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked…

Pre-trained model representations have demonstrated state-of-the-art performance in speech recognition, natural language processing, and other applications. Speech models, such as Bidirectional Encoder Representations from Transformers…

Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…

Representation learning from unlabeled data has been of major interest in artificial intelligence research. While self-supervised speech representation learning has been popular in the speech research community, very few works have…

Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder…

Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a…

Speech accents present a serious challenge to the performance of state-of-the-art end-to-end Automatic Speech Recognition (ASR) systems. Even with self-supervised learning and pre-training of ASR models, accent invariance is seldom…

On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets. When building such different models, we can benefit from training them jointly to take advantage of the…

We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo labels for…

We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech…