Related papers: CTC-TTS: LLM-based dual-streaming text-to-speech w…
When the complete source sentence is provided, Large Language Models (LLMs) perform excellently in offline machine translation even with a simple prompt "Translate the following sentence from [src lang] into [tgt lang]:". However, in many…
Conversational tutoring systems (CTSs) offer learning experiences driven by natural language interaction. They are known to promote high levels of cognitive engagement and benefit learning outcomes, particularly in reasoning tasks.…
Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy…
The task of Visual Text-to-Speech (VisualTTS), also known as video dubbing, aims to generate speech synchronized with the lip movements in an input video, in additional to being consistent with the content of input text and cloning the…
Dialogue serves as the most natural manner of human-computer interaction (HCI). Recent advancements in speech language models (SLM) have significantly enhanced speech-based conversational AI. However, these models are limited to turn-based…
This paper describes a novel text-to-speech (TTS) technique based on deep convolutional neural networks (CNN), without use of any recurrent units. Recurrent neural networks (RNN) have become a standard technique to model sequential data…
The neural codec language model (CLM) has demonstrated remarkable performance in text-to-speech (TTS) synthesis. However, troubled by ``recency bias", CLM lacks sufficient attention to coarse-grained information at a higher temporal scale,…
An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection…
Audio-visual alignment after dubbing is a challenging research problem. To this end, we propose a novel method, DubWise Multi-modal Large Language Model (LLM)-based Text-to-Speech (TTS), which can control the speech duration of synthesized…
Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradigm, requiring complete transcription and full reasoning…
Recent progress in text-to-speech (TTS) has achieved impressive naturalness and flexibility, especially with the development of large language model (LLM)-based approaches. However, existing autoregressive (AR) structures and large-scale…
We present a speaker conditioned text-to-speech (TTS) system aimed at addressing challenges in generating speech for unseen speakers and supporting diverse Indian languages. Our method leverages a diffusion-based TTS architecture, where a…
Large Language Models (LLMs) demonstrate impressive capabilities, yet interaction with these models is mostly facilitated through text. Using Text-To-Speech to synthesize LLM outputs typically results in notable latency, which is…
There has been limited evaluation of advanced Text-to-Speech (TTS) models with Mathematical eXpressions (MX) as inputs. In this work, we design experiments to evaluate quality and intelligibility of five TTS models through listening and…
Simultaneous speech translation (SST) takes streaming speech input and generates text translation on the fly. Existing methods either have high latency due to recomputation of input representations, or fall behind of offline ST in…
Diffusion-based Generative AI gains significant attention for its superior performance over other generative techniques like Generative Adversarial Networks and Variational Autoencoders. While it has achieved notable advancements in fields…
End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data. However, laborious data collection remains difficult for at least 95% of the languages over the world, which hinders the…
This paper describes Mixer-TTS, a non-autoregressive model for mel-spectrogram generation. The model is based on the MLP-Mixer architecture adapted for speech synthesis. The basic Mixer-TTS contains pitch and duration predictors, with the…
Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel…
Despite the advances in neural text to speech (TTS), many Arabic dialectal varieties remain marginally addressed, with most resources concentrated on Modern Spoken Arabic (MSA) and Gulf dialects, leaving Egyptian Arabic -- the most widely…