相关论文: K-Wav2vec 2.0: Automatic Speech Recognition based …

UniSpeech has achieved superior performance in cross-lingual automatic speech recognition (ASR) by explicitly aligning latent representations to phoneme units using multi-task self-supervised learning. While the learned representations…

Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically…

Single-word Automatic Speech Recognition (ASR) is a challenging task due to the lack of linguistic context and sensitivity to noise, pronunciation variation, and channel artifacts, especially in low-resource, communication-critical domains…

Deep learning techniques have been shown to be efficient in various tasks, especially in the development of speech recognition systems, that is, systems that aim to transcribe an audio sentence in a sequence of written words. Despite the…

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…

Self-supervised learning (SSL) has shown significant progress in speech processing tasks. However, despite the intrinsic randomness in the Transformer structure, such as dropout variants and layer-drop, improving the model-level consistency…

Recent advances in Audio-Visual Speech Recognition (AVSR) have led to unprecedented achievements in the field, improving the robustness of this type of system in adverse, noisy environments. In most cases, this task has been addressed…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Knowledge graphs (KGs) enhance the performance of large language models (LLMs) and search engines by providing structured, interconnected data that improves reasoning and context-awareness. However, KGs only focus on text data, thereby…

Dysarthric speech recognition has posed major challenges due to lack of training data and heavy mismatch in speaker characteristics. Recent ASR systems have benefited from readily available pretrained models such as wav2vec2 to improve the…

Recent advancements in machine learning have significantly improved speech recognition, but recognizing speech from non-fluent or accented speakers remains a challenge. Previous efforts, relying on rule-based pronunciation patterns, have…

In today's interconnected globe, moving abroad is more and more prevalent, whether it's for employment, refugee resettlement, or other causes. Language difficulties between natives and immigrants present a common issue on a daily basis,…

Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms.…

This paper presents SpecWav-Attack, an adversarial model for detecting speakers in anonymized speech. It leverages Wav2Vec2 for feature extraction and incorporates spectrogram resizing and incremental training for improved performance.…

Despite recent advances in voice separation methods, many challenges remain in realistic scenarios such as noisy recording and the limits of available data. In this work, we propose to explicitly incorporate the phonetic and linguistic…

Multilingual end-to-end(E2E) models have shown a great potential in the expansion of the language coverage in the realm of automatic speech recognition(ASR). In this paper, we aim to enhance the multilingual ASR performance in two ways,…

Self-supervised-learning-based pre-trained models for speech data, such as Wav2Vec 2.0 (W2V2), have become the backbone of many speech tasks. In this paper, to achieve speaker diarisation and speech recognition using a single model, a…

This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise…

We study training a single end-to-end (E2E) automatic speech recognition (ASR) model for three languages used in Kazakhstan: Kazakh, Russian, and English. We first describe the development of multilingual E2E ASR based on Transformer…

Non-parallel many-to-many voice conversion remains an interesting but challenging speech processing task. Recently, AutoVC, a conditional autoencoder based method, achieved excellent conversion results by disentangling the speaker identity…