Related papers: Neural Transducer Training: Reduced Memory Consump…

The recurrent neural network transducer (RNN-T) objective plays a major role in building today's best automatic speech recognition (ASR) systems for production. Similarly to the connectionist temporal classification (CTC) objective, the…

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrated that larger self-supervised feature extractors are crucial…

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then translate with machine translation (MT). A major cause of the performance gap is…

Recurrent neural transducer (RNN-T) is a promising end-to-end (E2E) model in automatic speech recognition (ASR). It has shown superior performance compared to traditional hybrid ASR systems. However, training RNN-T from scratch is still…

Various hardware accelerators have been developed for energy-efficient and real-time inference of neural networks on edge devices. However, most training is done on high-performance GPUs or servers, and the huge memory and computing costs…

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…

Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech…

Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based acoustic models is used to deal with this problem, but it…

End-to-end (E2E) automatic speech recognition (ASR) systems directly map acoustics to words using a unified model. Previous works mostly focus on E2E training a single model which integrates acoustic and language model into a whole.…

Self-supervised learning (SSL) has proven vital in speech and audio-related applications. The paradigm trains a general model on unlabeled data that can later be used to solve specific downstream tasks. This type of model is costly to train…

In this work we evaluate the utility of synthetic data for training automatic speech recognition (ASR). We use the ASR training data to train a text-to-speech (TTS) system similar to FastSpeech-2. With this TTS we reproduce the original…

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer…

Multi-channel inputs offer several advantages over single-channel, to improve the robustness of on-device speech recognition systems. Recent work on multi-channel transformer, has proposed a way to incorporate such inputs into end-to-end…

We present a method for transferring pre-trained self-supervised (SSL) speech representations to multiple languages. There is an abundance of unannotated speech, so creating self-supervised representations from raw audio and fine-tuning on…

Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…

Sustainable artificial intelligence focuses on data, hardware, and algorithms to make machine learning models more environmentally responsible. In particular, machine learning models for speech representations are computationally expensive,…

Automatic Speech Recognition (ASR) based on Recurrent Neural Network Transducers (RNN-T) is gaining interest in the speech community. We investigate data selection and preparation choices aiming for improved robustness of RNN-T ASR to…