Related papers: On the Robust Approximation of ASR Metrics

We propose a bottom-up framework for automatic speech recognition (ASR) in syllable-based languages by unifying language-universal articulatory attribute modeling with syllable-level prediction. The system first recognizes sequences or…

Many automatic speech recognition (ASR) data sets include a single pre-defined test set consisting of one or more speakers whose speech never appears in the training set. This "hold-speaker(s)-out" data partitioning strategy, however, may…

Aiming at reducing the reliance on expensive human annotations, data synthesis for Automatic Speech Recognition (ASR) has remained an active area of research. While prior work mainly focuses on synthetic speech generation for ASR data…

In Speech Emotion Recognition (SER), textual data is often used alongside audio signals to address their inherent variability. However, the reliance on human annotated text in most research hinders the development of practical SER systems.…

In the wake of the surging tide of deep learning over the past decade, Automatic Speech Recognition (ASR) has garnered substantial attention, leading to the emergence of numerous publicly accessible ASR systems that are actively being…

Bootstrapping speech recognition on limited data resources has been an area of active research for long. The recent transition to all-neural models and end-to-end (E2E) training brought along particular challenges as these models are known…

Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

Automatic Speech Recognition (ASR) systems can be trained to achieve remarkable performance given large amounts of manually transcribed speech, but large labeled data sets can be difficult or expensive to acquire for all languages of…

Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address…

The ongoing research scenario for automatic speech recognition (ASR) envisions a clear division between end-to-end approaches and classic modular systems. Even though a high-level comparison between the two approaches in terms of their…

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is…

We investigate continued pretraining (CPT) for adapting wav2vec2-bert-2.0 to Swahili automatic speech recognition (ASR). Our approach combines unlabeled audio with limited labeled data through pseudo-labeled CPT followed by supervised…

The best-performing approaches for scholarly document quality prediction are based on embedding models. In addition to their performance when used in classifiers, embedding models can also provide predictions even for words that were not…

Automatic speech recognition (ASR) systems have achieved strong performance on general transcription tasks. However, they continue to struggle with recognizing rare named entities and adapting to domain mismatches. In contrast, large…

In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced.…

In this work, we try to answer two questions: Can deeply learned features with discriminative power benefit an ASR system's robustness to acoustic variability? And how to learn them without requiring framewise labelled sequence training…

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…