Related papers: Adaptive hybrid speech coding with a MLP LPC struc…

Silent speech decoding, which performs unvocalized human speech recognition from electroencephalography/electromyography (EEG/EMG), increases accessibility for speech-impaired humans. However, data collection is difficult and performed…

In this paper we propose a new parameterization algorithm based on nonlinear prediction, which is an extension of the classical LPC parameters. The parameters performances are estimated by two different methods: the Arithmetic-Harmonic…

Accent variability has posed a huge challenge to automatic speech recognition~(ASR) modeling. Although one-hot accent vector based adaptation systems are commonly used, they require prior knowledge about the target accent and cannot handle…

In recent years, End-to-End speech recognition technology based on deep learning has developed rapidly. Due to the lack of Turkish speech data, the performance of Turkish speech recognition system is poor. Firstly, this paper studies a…

Neural audio codecs (NACs) provide compact latent speech representations in the form of sequences of continuous vectors or discrete tokens. In this work, we investigate how these two types of speech representations compare when used as…

Neural network based approaches to speech enhancement have shown to be particularly powerful, being able to leverage a data-driven approach to result in a significant performance gain versus other approaches. Such approaches are reliant on…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

Deep learning-based speech enhancement methods have significantly improved speech quality and intelligibility. Convolutional neural networks (CNNs) have been proven to be essential components of many high-performance models. In this paper,…

As deep speech enhancement algorithms have recently demonstrated capabilities greatly surpassing their traditional counterparts for suppressing noise, reverberation and echo, attention is turning to the problem of packet loss concealment…

While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language…

Large speech models are rapidly gaining traction in research community. As a result, model compression has become an important topic, so that these models can fit in memory and be served with reduced cost. Practical approaches for…

This paper focuses on a newly developed transparent nADPCMB MLT speech coding algorithm. Our coder first decomposes the narrowband speech signal in subbands, a non linear ADPCM scheme is then performed in each subband. The signal subband…

This study investigates the problem of learning linear block codes optimized for Belief-Propagation decoders significantly improving performance compared to the state-of-the-art. Our previous research is extended with an enhanced system…

Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…

Interfering sources, background noise and reverberation degrade speech quality and intelligibility in hearing aid applications. In this paper, we present an adaptive algorithm aiming at dereverberation, noise and interferer reduction and…

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and independent learned embeddings for each speaker. The aim of…

Recent advancements in Neural Audio Codec (NAC) models have inspired their use in various speech processing tasks, including speech enhancement (SE). In this work, we propose a novel, efficient SE approach by leveraging the pre-quantization…

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Semantic representation learning for sentences is an important and well-studied problem in NLP. The current trend for this task involves training a Transformer-based sentence encoder through a contrastive objective with text, i.e.,…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…