Related papers: BitTTS: Highly Compact Text-to-Speech Using 1.58-b…

Text-to-image diffusion models have emerged as a powerful framework for high-quality image generation given textual prompts. Their success has driven the rapid development of production-grade diffusion models that consistently increase in…

Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary…

Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on…

As an effective technique to achieve the implementation of deep neural networks in edge devices, model quantization has been successfully applied in many practical applications. No matter the methods of quantization aware training (QAT) or…

Contemporary machine learning models, such as language models, are powerful, but come with immense resource requirements both at training and inference time. It has been shown that decoder-only language models can be trained to a…

With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While most research focuses on how to accurately retain…

Existing autoregressive large-scale text-to-speech (TTS) models have advantages in speech naturalness, but their token-by-token generation mechanism makes it difficult to precisely control the duration of synthesized speech. This becomes a…

Large language models (LLMs) have wide applications in the field of natural language processing(NLP), such as GPT-4 and Llama. However, with the exponential growth of model parameter sizes, LLMs bring significant resource overheads. Low-bit…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Personalized TTS is an exciting and highly desired application that allows users to train their TTS voice using only a few recordings. However, TTS training typically requires many hours of recording and a large model, making it unsuitable…

State-of-the-art text-to-speech (TTS) systems require several hours of recorded speech data to generate high-quality synthetic speech. When using reduced amounts of training data, standard TTS models suffer from speech quality and…

Large Language Models (LLMs) have been extensively researched and used in both academia and industry since the rise in popularity of the Transformer model, which demonstrates excellent performance in AI. However, the computational demands…

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT…

We propose a pretraining method to use Self-Supervised Speech (SSS) model to creating more compact Speech-to-text Translation. In contrast to using the SSS model for initialization, our method is more suitable to memory constrained scenario…

Recently, pre-trained Transformer based language models, such as BERT, have shown great superiority over the traditional methods in many Natural Language Processing (NLP) tasks. However, the computational cost for deploying these models is…

Recent studies introduced effective compression techniques for Large Language Models (LLMs) via post-training quantization or low-bit weight representation. Although quantized weights offer storage efficiency and allow for faster inference,…

Modern speaker verification (SV) systems typically demand expensive storage and computing resources, thereby hindering their deployment on mobile devices. In this paper, we explore adaptive neural network quantization for lightweight…

With the popularity of the recent Transformer-based models represented by BERT, GPT-3 and ChatGPT, there has been state-of-the-art performance in a range of natural language processing tasks. However, the massive computations, huge memory…

Text-to-speech(TTS) has undergone remarkable improvements in performance, particularly with the advent of Denoising Diffusion Probabilistic Models (DDPMs). However, the perceived quality of audio depends not solely on its content, pitch,…

Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…