Related papers: TinySpeech: Attention Condensers for Deep Speech R…

It is highly desirable that speech enhancement algorithms can achieve good performance while keeping low latency for many applications, such as digital hearing aids, acoustically transparent hearing devices, and public address systems. To…

Sparse tensors appear frequently in distributed deep learning, either as a direct artifact of the deep neural network's gradients, or as a result of an explicit sparsification process. Existing communication primitives are agnostic to the…

In collaborative intelligence applications, part of a deep neural network (DNN) is deployed on a relatively low-complexity device such as a mobile phone or edge device, and the remainder of the DNN is processed where more computing…

Transformer-based acoustic modeling has achieved great suc-cess for both hybrid and sequence-to-sequence speech recogni-tion. However, it requires access to the full sequence, and thecomputational cost grows quadratically with respect to…

A deep learning approach has been widely applied in sequence modeling problems. In terms of automatic speech recognition (ASR), its performance has significantly been improved by increasing large speech corpus and deeper neural network.…

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…

Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory size. We find that the memory bottleneck is due to the imbalanced memory distribution in convolutional neural network (CNN) designs: the first…

Reconstructing natural speech from neural activity is vital for enabling direct communication via brain-computer interfaces. Previous efforts have explored the conversion of neural recordings into speech using complex deep neural network…

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…

Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task. However, there is still a significant…

Deep neural networks have become an indispensable technique for audio source separation (ASS). It was recently reported that a variant of CNN architecture called MMDenseNet was successfully employed to solve the ASS problem of estimating…

To facilitate the evolution of edge intelligence in ever-changing environments, we study on-device incremental learning constrained in limited computation resource in this paper. Current on-device training methods just focus on efficient…

Current text-to-speech (TTS) models face a persistent limitation: autoregressive (AR) models suffer from low generation efficiency, while modern non-autoregressive (NAR) models experience high latency due to their unordered temporal nature.…

Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size and computations for low-power edge devices drastically…

Clipping is a common nonlinear distortion that occurs whenever the input or output of an audio system exceeds the supported range. This phenomenon undermines not only the perception of speech quality but also downstream processes utilizing…

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Voice recognition and speaker identification are vital for applications in security and personal assistants. This paper presents a lightweight 1D-Convolutional Neural Network (1D-CNN) designed to perform speaker identification on minimal…

Executing deep neural networks (DNNs) on edge artificial intelligence (AI) devices enables various autonomous mobile computing applications. However, the memory budget of edge AI devices restricts the number and complexity of DNNs allowed…

Language models have gained significant interest due to their general-purpose capabilities, which appear to emerge as models are scaled to increasingly larger parameter sizes. However, these large models impose stringent requirements on…

As Machine Learning (ML) becomes integral to Cyber-Physical Systems (CPS), there is growing interest in shifting training from traditional cloud-based to on-device processing (TinyML), for example, due to privacy and latency concerns.…