相关论文: Fast query-by-example speech search using separabl…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Acoustic word embeddings (AWEs) are fixed-dimensional vector representations of speech segments that encode phonetic content so that different realisations of the same word have similar embeddings. In this paper we explore semantic AWE…

This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is…

Target speaker extraction aims to separate the voice of a specific speaker from mixed speech. Traditionally, this process has relied on extracting a speaker embedding from a reference speech, in which a speaker recognition model is…

Many speech processing tasks involve measuring the acoustic similarity between speech segments. Acoustic word embeddings (AWE) allow for efficient comparisons by mapping speech segments of arbitrary duration to fixed-dimensional vectors.…

Target Speaker Extraction (TSE) uses a reference cue to extract the target speech from a mixture. In TSE systems relying on audio cues, the speaker embedding from the enrolled speech is crucial to performance. However, these embeddings may…

End-to-end (E2E) automatic speech recognition (ASR) methods exhibit remarkable performance. However, since the performance of such methods is intrinsically linked to the context present in the training data, E2E-ASR methods do not perform…

In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain…

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of…

Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a…

The amount of audio data available on public websites is growing rapidly, and an efficient mechanism for accessing the desired data is necessary. We propose a content-based audio retrieval method that can retrieve a target audio that is…

Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods…

In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We…

Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…

End-to-end (E2E) systems have achieved competitive results compared to conventional hybrid hidden Markov model (HMM)-deep neural network based automatic speech recognition (ASR) systems. Such E2E systems are attractive due to the lack of…

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…

Models of acoustic word embeddings (AWEs) learn to map variable-length spoken word segments onto fixed-dimensionality vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding…

Embedding-based retrieval aims to learn a shared semantic representation space for both queries and items, enabling efficient and effective item retrieval through approximate nearest neighbor (ANN) algorithms. In current industrial…

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

The end-to-end (E2E) automatic speech recognition (ASR) systems are often required to operate in reverberant conditions, where the long-term sub-band envelopes of the speech are temporally smeared. In this paper, we develop a feature…