相关论文: The Faetar Benchmark: Speech Recognition in a Very…

In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust…

Large speech foundation models achieve strong performance across many domains, but they often require adaptation to handle local needs such as code-switching, where speakers mix languages within the same utterance. Direct fine-tuning of…

It is well known that many machine learning systems demonstrate bias towards specific groups of individuals. This problem has been studied extensively in the Facial Recognition area, but much less so in Automatic Speech Recognition (ASR).…

In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task. Our main approach is based on the LASER toolkit (Language-Agnostic SEntence Representations), which uses an encoder-decoder…

The landscape of extremely low-resource machine translation (MT) is characterized by perplexing variability in reported performance, often making results across different language pairs difficult to contextualize. For researchers focused on…

This paper tests the hypothesis that distinctive feature classifiers anchored at phonetic landmarks can be transferred cross-lingually without loss of accuracy. Three consonant voicing classifiers were developed: (1) manually selected…

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

Speech recognition applications cover a range of different audio and text distributions, with different speaking styles, background noise, transcription punctuation and character casing. However, many speech recognition systems require…

In this work, we explore a multimodal semi-supervised learning approach for punctuation prediction by learning representations from large amounts of unlabelled audio and text data. Conventional approaches in speech processing typically use…

Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production…

Semantic segmentation is a core component of discourse analysis, yet existing models are primarily developed and evaluated on high-resource written text, limiting their effectiveness on low-resource spoken varieties. In particular,…

Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benefiting from the diverse data sources such as different…

Wav2Vec2.0 is a state-of-the-art model which learns speech representations through unlabeled speech data, aka, self supervised learning. The pretrained model is then fine tuned on small amounts of labeled data to use it for speech-to-text…

Popular ASR benchmarks such as Librispeech and Switchboard are limited in the diversity of settings and speakers they represent. We introduce a set of benchmarks matching real-life conditions, aimed at spotting possible biases and…

Audiovisual speech recognition (AVSR) combines acoustic and visual cues to improve transcription robustness under challenging conditions but remains out of reach for most under-resourced languages due to the lack of labeled video corpora…

Automatic speech recognition systems have achieved remarkable performance on fluent speech but continue to degrade significantly when processing stuttered speech, a limitation that is particularly acute for low-resource languages like…

Automatic speech recognition (ASR) for dysarthric speech remains challenging due to data scarcity, particularly in non-English languages. To address this, we fine-tune a voice conversion model on English dysarthric speech (UASpeech) to…

Existing resources for Automatic Speech Recognition in Portuguese are mostly focused on Brazilian Portuguese, leaving European Portuguese (EP) and other varieties under-explored. To bridge this gap, we introduce CAM\~OES, the first open…

Unsupervised and self-supervised learning methods have leveraged unlabelled data to improve the pretrained models. However, these methods need significantly large amount of unlabelled data and the computational cost of training models with…

Deepfake speech represents a real and growing threat to systems and society. Many detectors have been created to aid in defense against speech deepfakes. While these detectors implement myriad methodologies, many rely on low-level fragments…