相关论文: PhasePerturbation: Speech Data Augmentation via Ph…

For real-time speech enhancement (SE) including noise suppression, dereverberation and acoustic echo cancellation, the time-variance of the audio signals becomes a severe challenge. The causality and memory usage limit that only the…

During the entire training process of the ASR model, the intensity of data augmentation and the approach of calculating training loss are applied in a regulated manner based on preset parameters. For example, SpecAugment employs a…

Time-frequency (T-F) domain masking is a mainstream approach for single-channel speech enhancement. Recently, focuses have been put to phase prediction in addition to amplitude prediction. In this paper, we propose a…

How important are different temporal speech modulations for speech recognition? We answer this question from two complementary perspectives. Firstly, we quantify the amount of phonetic \textit{information} in the modulation spectrum of…

Singing voice separation aims to separate music into vocals and accompaniment components. One of the major constraints for the task is the limited amount of training data with separated vocals. Data augmentation techniques such as random…

End-to-end models have gradually become the preferred option for automatic speech recognition (ASR) applications. During the training of end-to-end ASR, data augmentation is a quite effective technique for regularizing the neural networks.…

Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing with low-resource tasks. Using recent advances in speech…

Attention has become one of the most commonly used mechanisms in deep learning approaches. The attention mechanism can help the system focus more on the feature space's critical regions. For example, high amplitude regions can play an…

Foundation models have shown superior performance for speech emotion recognition (SER). However, given the limited data in emotion corpora, finetuning all parameters of large pre-trained models for SER can be both resource-intensive and…

Chinese Automatic Speech Recognition (ASR) error correction presents significant challenges due to the Chinese language's unique features, including a large character set and borderless, morpheme-based structure. Current mainstream models…

Speech enhancement has seen great improvement in recent years mainly through contributions in denoising, speaker separation, and dereverberation methods that mostly deal with environmental effects on vocal audio. To enhance speech beyond…

Speech disfluency commonly occurs in conversational and spontaneous speech. However, standard Automatic Speech Recognition (ASR) models struggle to accurately recognize these disfluencies because they are typically trained on fluent…

Aspect-based sentiment analysis (ABSA) involves identifying sentiment towards specific aspect terms in a sentence and allows us to uncover nuanced perspectives and attitudes on particular aspects of a product, service, or topic. However,…

Cross-domain speech enhancement (SE) is often faced with severe challenges due to the scarcity of noise and background information in an unseen target domain, leading to a mismatch between training and test conditions. This study puts…

In this work, we present our submission to the Speech Accessibility Project challenge for dysarthric speech recognition. We integrate parameter-efficient fine-tuning with latent audio representations to improve an encoder-decoder ASR…

Speech deepfake detection (SDD) systems perform well on standard benchmarks datasets but often fail to generalize to expressive and emotional spoofing attacks. Many methods rely on spoof-heavy training data, learning dataset-specific…

Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of…

Stuttering is a neuro-developmental speech impairment characterized by uncontrolled utterances (interjections) and core behaviors (blocks, repetitions, and prolongations), and is caused by the failure of speech sensorimotors. Due to its…

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

In this paper, we investigate the impact of incorporating timestamp-based alignment between Automatic Speech Recognition (ASR) transcripts and Speaker Diarization (SD) outputs on Speech Emotion Recognition (SER) accuracy. Misalignment…