Related papers: SpecTokenizer: A Lightweight Streaming Codec in th…
Deep neural network based full-band speech enhancement systems face challenges of high demand of computational resources and imbalanced frequency distribution. In this paper, a light-weight full-band model is proposed with two dedicated…
Convolutional Neural Networks (CNN) have been the centerpiece of many applications including but not limited to computer vision, speech processing, and Natural Language Processing (NLP). However, the computationally expensive convolution…
This paper presents a novel approach to neuromorphic audio processing by integrating the strengths of Spiking Neural Networks (SNNs), Transformers, and high-performance computing (HPC) into the HPCNeuroNet architecture. Utilizing the Intel…
In this paper, we propose MDCTCodec, an efficient lightweight end-to-end neural audio codec based on the modified discrete cosine transform (MDCT). The encoder takes the MDCT spectrum of audio as input, encoding it into a continuous latent…
Recent years have witnessed the dramatic growth of Internet video traffic, where the video bitstreams are often compressed and delivered in low quality to fit the streamer's uplink bandwidth. To alleviate the quality degradation, it comes…
Spectrograms have been widely used in Convolutional Neural Networks based schemes for acoustic scene classification, such as the STFT spectrogram and the MFCC spectrogram, etc. They have different time-frequency characteristics,…
State-of-the-art audio captioning methods typically use the encoder-decoder structure with pretrained audio neural networks (PANNs) as encoders for feature extraction. However, the convolution operation used in PANNs is limited in capturing…
Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation.…
Mobile and embedded machine learning developers frequently have to compromise between two inferior on-device deployment strategies: sacrifice accuracy and aggressively shrink their models to run on dedicated low-power cores; or sacrifice…
Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. With recent state-of-the-art attention-based automatic speech recognition (ASR) structure, NAR can realize promising real-time factor (RTF)…
Speech enhancement (SE) aims to extract the clean waveform from noise-contaminated measurements to improve the speech quality and intelligibility. Although learning-based methods can perform much better than traditional counterparts, the…
State-of-the-art sequence-to-sequence acoustic networks, that convert a phonetic sequence to a sequence of spectral features with no explicit prosody prediction, generate speech with close to natural quality, when cascaded with neural…
Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often…
Recent advancements in neural audio codecs have not only enabled superior audio compression but also enhanced speech synthesis techniques. Researchers are now exploring their potential as universal acoustic feature extractors for a broader…
Speech tokenization is the task of representing speech signals as a sequence of discrete units. Such representations can be later used for various downstream tasks including automatic speech recognition, text-to-speech, etc. More relevant…
Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…
Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text, thus enabling the use of speech as an input to the widely successful large language models (LLMs). Currently,…
We investigate training end-to-end speech recognition models with the recurrent neural network transducer (RNN-T): a streaming, all-neural, sequence-to-sequence architecture which jointly learns acoustic and language model components from…
Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones. A recent trend in speech and speaker recognition consists in discovering these representations starting from raw…
Recent studies show that self-attentions behave like low-pass filters (as opposed to convolutions) and enhancing their high-pass filtering capability improves model performance. Contrary to this idea, we investigate existing…