Related papers: Overlap-Add Windows with Maximum Energy Concentrat…
This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…
Neuro-symbolic AI is gaining traction in domains such as large language models, scientific discovery, and autonomous systems due to its ability to combine perception with structured reasoning. However, its deployment is often constrained by…
In recent work, redressed warped frames have been introduced for the analysis and synthesis of audio signals with non-uniform frequency and time resolutions. In these frames, the allocation of frequency bands or time intervals of the…
In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features…
Despite recent advances, Automatic Speech Recognition (ASR) systems are still far from perfect. Typical errors include acronyms, named entities, and domain-specific special words for which little or no labeled data is available. To address…
Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…
Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…
Recent innovations in self-supervised representation learning have led to remarkable advances in natural language processing. That said, in the speech processing domain, self-supervised representation learning-based systems are not yet…
Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending…
In this paper, we propose a novel approach for the transcription of speech conversations with natural speaker overlap, from single channel speech recordings. The proposed model is a combination of a speaker diarization system and a hybrid…
Speech processing systems currently do not support the vast majority of languages, in part due to the lack of data in low-resource languages. Cross-lingual transfer offers a compelling way to help bridge this digital divide by incorporating…
Whispered speech as an acceptable form of human-computer interaction is gaining traction. Systems that address multiple modes of speech require a robust front-end speech classifier. Performance of whispered vs normal speech classification…
We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…
The ability to cancel an OFDM signal is important to many wireless communication systems including Power-Domain Non-orthogonal Multiple Access (PD-NOMA), Rate-Splitting Multiple Access (RSMA), and spectrum underlay for dynamic spectrum…
Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…
In this work, we derive a generic overcomplete frame thresholding scheme based on risk minimization. Overcomplete frames being favored for analysis tasks such as classification, regression or anomaly detection, we provide a way to leverage…
Recent advancements in textless speech-to-speech translation systems have been driven by the adoption of self-supervised learning techniques. Although most state-of-the-art systems adopt a similar architecture to transform source language…
Neural summarization models suffer from the fixed-size input limitation: if text length surpasses the model's maximal number of input tokens, some document content (possibly summary-relevant) gets truncated Independently summarizing windows…
This paper describes our submission to ICASSP 2022 Multi-channel Multi-party Meeting Transcription (M2MeT) Challenge. For Track 1, we propose several approaches to empower the clustering-based speaker diarization system to handle overlapped…
Automatic speaker verification systems are vulnerable to a variety of access threats, prompting research into the formulation of effective spoofing detection systems to act as a gate to filter out such spoofing attacks. This study…