相关论文: Semi-supervised acoustic and language model traini…

We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind. We discuss SSL for AMs in a small…

This work evaluated several cutting-edge large-scale foundation models based on self-supervision or weak supervision, including SeamlessM4T, SeamlessM4T v2, and Whisper-large-v3, on three code-switched corpora. We found that self-supervised…

We address the problem of efficient acoustic-model refinement (continuous retraining) using semi-supervised and active learning for a low resource Indian language, wherein the low resource constraints are having i) a small labeled corpus…

This research addresses the problem of acoustic modeling of low-resource languages for which transcribed training data is absent. The goal is to learn robust frame-level feature representations that can be used to identify and distinguish…

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

Self-supervised learning (SSL) based speech foundation models have been applied to a wide range of ASR tasks. However, their application to dysarthric and elderly speech via data-intensive parameter fine-tuning is confronted by in-domain…

The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption,…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

Training multilingual automatic speech recognition (ASR) systems is challenging because acoustic and lexical information is typically language specific. Training multilingual system for Indic languages is even more tougher due to lack of…

In end-to-end automatic speech recognition system, one of the difficulties for language expansion is the limited paired speech and text training data. In this paper, we propose a novel method to generate augmented samples with unpaired…

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to…

This paper describes the NTNU ASR system participating in the Interspeech 2020 Non-Native Children's Speech ASR Challenge supported by the SIG-CHILD group of ISCA. This ASR shared task is made much more challenging due to the coexisting…

In this work, we investigated the teacher-student training paradigm to train a fully learnable multi-channel acoustic model for far-field automatic speech recognition (ASR). Using a large offline teacher model trained on beamformed audio,…

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…

Source separation can improve automatic speech recognition (ASR) under multi-party meeting scenarios by extracting single-speaker signals from overlapped speech. Despite the success of self-supervised learning models in single-channel…

Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial amount of paired speech-text and unlabeled speech, which is…

Recent work in the field of speech enhancement (SE) has involved the use of self-supervised speech representations (SSSRs) as feature transformations in loss functions. However, in prior work, very little attention has been paid to the…

Recent advances in machine learning have demonstrated that multi-modal pre-training can improve automatic speech recognition (ASR) performance compared to randomly initialized models, even when models are fine-tuned on uni-modal tasks.…