相关论文: BitTTS: Highly Compact Text-to-Speech Using 1.58-b…

In recent years, a great deal of attention has been paid to the Transformer network for speech recognition tasks due to its excellent model performance. However, the Transformer network always involves heavy computation and large number of…

Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using…

Vision Transformers (ViTs) have achieved remarkable performance in various image classification tasks by leveraging the attention mechanism to process image patches as tokens. However, the high computational and memory demands of ViTs pose…

Large language models (LLMs) have revolutionized language processing, delivering outstanding results across multiple applications. However, deploying LLMs on edge devices poses several challenges with respect to memory, energy, and compute…

Different languages have distinct phonetic systems and vary in their prosodic features making it challenging to develop a Text-to-Speech (TTS) model that can effectively synthesise speech in multilingual settings. Furthermore, TTS…

Large Language Models (LLMs) are proficient in natural language processing tasks, but their deployment is often restricted by extensive parameter sizes and computational demands. This paper focuses on post-training quantization (PTQ) in…

With the emergence of neural audio codecs, which encode multiple streams of discrete tokens from audio, large language models have recently gained attention as a promising approach for zero-shot Text-to-Speech (TTS) synthesis. Despite the…

Large-scale universal speech models (USM) are already used in production. However, as the model size grows, the serving cost grows too. Serving cost of large models is dominated by model size that is why model size reduction is an important…

Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures, creating substantial barriers for resource-constrained research teams. In this report, we…

Transformer-based pre-training models like BERT have achieved remarkable performance in many natural language processing tasks.However, these models are both computation and memory expensive, hindering their deployment to…

The rapid advancement of large language models (LLMs) has led to significant improvements in natural language processing but also poses challenges due to their high computational and energy demands. This paper introduces a series of…

Scaling model size significantly challenges the deployment and inference of Large Language Models (LLMs). Due to the redundancy in LLM weights, recent research has focused on pushing weight-only quantization to extremely low-bit (even down…

Text-to-Speech (TTS) models can generate natural, human-like speech across multiple languages by transforming phonemes into waveforms. However, multilingual TTS remains challenging due to discrepancies in phoneme vocabularies and variations…

Transformer-based text to speech (TTS) model (e.g., Transformer TTS~\cite{li2019neural}, FastSpeech~\cite{ren2019fastspeech}) has shown the advantages of training and inference efficiency over RNN-based model (e.g.,…

Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between…

Large language models (LLMs) have achieved remarkable advancements in natural language processing, showcasing exceptional performance across various tasks. However, the expensive memory and computational requirements present significant…

We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and to generate text during inference. Our method, which we…

Few-shot speaker adaptation is a specific Text-to-Speech (TTS) system that aims to reproduce a novel speaker's voice with a few training data. While numerous attempts have been made to the few-shot speaker adaptation system, there is still…

Toxicity is a prevalent social behavior that involves the use of hate speech, offensive language, bullying, and abusive speech. While text-based approaches for toxicity detection are common, there is limited research on processing speech…

Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech…