Related papers: A study on speech enhancement using exponent-only …

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…

We introduce Lookup-Table Language Models (LookupLM), a method for scaling up the size of RNN language models with only a constant increase in the floating point operations, by increasing the expressivity of the embedding table. In…

In this paper we propose a lightweight model for frequency bandwidth extension of speech signals, increasing the sampling frequency from 8kHz to 16kHz while restoring the high frequency content to a level almost indistinguishable from the…

As a hybrid of artificial intelligence and quantum computing, quantum neural networks (QNNs) have gained significant attention as a promising application on near-term, noisy intermediate-scale quantum (NISQ) devices. Conventional QNNs are…

We propose Factorization Memory, an efficient recurrent neural network (RNN) architecture that achieves performance comparable to Transformer models on short-context language modeling tasks while also demonstrating superior generalization…

Nowadays, most of the objective speech quality assessment tools (e.g., perceptual evaluation of speech quality (PESQ)) are based on the comparison of the degraded/processed speech with its clean counterpart. The need of a "golden" reference…

Quantization has become a mainstream compression technique for reducing model size, computational requirements, and energy consumption for modern deep neural networks (DNNs). With improved numerical support in recent hardware, including…

Recurrent neural networks (RNNs) with deep test-time memorization modules, such as Titans and TTT, represent a promising, linearly-scaling paradigm distinct from Transformers. While these expressive models do not yet match the peak…

We propose a method using a long short-term memory (LSTM) network to estimate the noise power spectral density (PSD) of single-channel audio signals represented in the short time Fourier transform (STFT) domain. An LSTM network common to…

Statistical language models are central to many applications that use semantics. Recurrent Neural Networks (RNN) are known to produce state of the art results for language modelling, outperforming their traditional n-gram counterparts in…

Recurrent neural networks have achieved excellent performance in many applications. However, on portable devices with limited resources, the models are often too large to deploy. For applications on the server with large scale concurrent…

In this paper, we propose a type of neural network with feedback learning in the time domain called FTNet for monaural speech enhancement, where the proposed network consists of three principal components. The first part is called stage…

The emergence of large language models (LLMs) like GPT-4 has revolutionized natural language processing (NLP), enabling diverse, complex tasks. However, extensive token counts lead to high computational and financial burdens. To address…

Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is especially useful for memory-intensive recurrent neural…

In this work, we propose a low-bit training framework for convolutional neural networks, which is built around a novel multi-level scaling (MLS) tensor format. Our framework focuses on reducing the energy consumption of convolution…

Deploying federated learning (FL) over wireless networks with resource-constrained devices requires balancing between accuracy, energy efficiency, and precision. Prior art on FL often requires devices to train deep neural networks (DNNs)…

Post-training quantization (PTQ) is a powerful technique for model compression, reducing the numerical precision in neural networks without additional training overhead. Recent works have investigated adopting 8-bit floating-point…

Recent end-to-end automatic speech recognition (ASR) models have become increasingly larger, making them particularly challenging to be deployed on resource-constrained devices. Model quantisation is an effective solution that sometimes…

Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for real-world applications is constrained by substantial computational costs and latency issues.…

This paper proposes an efficient reconfigurable hardware design for speech enhancement based on multi band spectral subtraction algorithm and involving both magnitude and phase components. Our proposed design is novel as it estimates…