Related papers: Joint Masked CPC and CTC Training for ASR

For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a…

This paper proposes a method to relax the conditional independence assumption of connectionist temporal classification (CTC)-based automatic speech recognition (ASR) models. We train a CTC-based ASR model with auxiliary CTC losses in…

This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over…

In this work, we compare from-scratch sequence-level cross-entropy (full-sum) training of Hidden Markov Model (HMM) and Connectionist Temporal Classification (CTC) topologies for automatic speech recognition (ASR). Besides accuracy, we…

Recent techniques for speech deepfake detection often rely on pre-trained self-supervised models. These systems, initially developed for Automatic Speech Recognition (ASR), have proved their ability to offer a meaningful representation of…

This paper proposes a novel approach to pre-train encoder-decoder sequence-to-sequence (seq2seq) model with unpaired speech and transcripts respectively. Our pre-training method is divided into two stages, named acoustic pre-trianing and…

ASR systems based on self-supervised acoustic pretraining and CTC fine-tuning achieve strong performance on native speech but remain sensitive to accent variability. We investigate supervised contrastive learning (SupCon) as a lightweight,…

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

Recently, pioneer work finds that speech pre-trained models can solve full-stack speech processing tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information.…

We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions. We perform experiments on the standard LibriSpeech…

Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minutes of labeled data. However, these systems are…

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from…

Combination approaches for speech recognition (ASR) systems cover structured sentence-level or word-based merging techniques as well as combination of model scores during beam search. In this work, we compare model combination across…

We present a bidirectional unsupervised model pre-training (UPT) method and apply it to children's automatic speech recognition (ASR). An obstacle to improving child ASR is the scarcity of child speech databases. A common approach to…

Siamese networks have shown effective results in unsupervised visual representation learning. These models are designed to learn an invariant representation of two augmentations for one input by maximizing their similarity. In this paper,…

In this paper, we propose a three-stage training methodology to improve the speech recognition accuracy of low-resource languages. We explore and propose an effective combination of techniques such as transfer learning, encoder freezing,…

In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn representations suitable for recognizing a word-level sequence. However, the huge abstraction gap between input acoustic signals and output linguistic…

It is challenging to extract semantic meanings directly from audio signals in spoken language understanding (SLU), due to the lack of textual information. Popular end-to-end (E2E) SLU models utilize sequence-to-sequence automatic speech…

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…

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…