Related papers: Real-Time Streaming Mel Vocoding with Generative F…

Mel Frequency Cepstral Coefficients (MFCCs) are the most popularly used speech features in most speech and speaker recognition applications. In this work, we propose a modified Mel filter bank to extract MFCCs from subsampled speech. We…

Language models (LMs) have recently flourished in natural language processing and computer vision, generating high-fidelity texts or images in various tasks. In contrast, the current speech generative models are still struggling regarding…

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…

Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acoustic information as possible. However, in some models…

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively…

Recent developments in generative models have shown that deep learning combined with traditional digital signal processing (DSP) techniques could successfully generate convincing violin samples [1], that source-excitation combined with…

Recent advances in visually-induced audio generation are based on sampling short, low-fidelity, and one-class sounds. Moreover, sampling 1 second of audio from the state-of-the-art model takes minutes on a high-end GPU. In this work, we…

Streaming speech-to-text translation (StreamST) is the task of automatically translating speech while incrementally receiving an audio stream. Unlike simultaneous ST (SimulST), which deals with pre-segmented speech, StreamST faces the…

We propose DarkStream, a streaming speech synthesis model for real-time speaker anonymization. To improve content encoding under strict latency constraints, DarkStream combines a causal waveform encoder, a short lookahead buffer, and…

In this work, we propose a new mathematical vocoder algorithm(modified spectral inversion) that generates a waveform from acoustic features without phase estimation. The main benefit of using our proposed method is that it excludes the…

Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel. AlignTTS is based on a Feed-Forward Transformer which generates mel-spectrum from a sequence of characters, and the duration of…

We describe a sequence-to-sequence neural network which directly generates speech waveforms from text inputs. The architecture extends the Tacotron model by incorporating a normalizing flow into the autoregressive decoder loop. Output…

Recently, Transformer based end-to-end models have achieved great success in many areas including speech recognition. However, compared to LSTM models, the heavy computational cost of the Transformer during inference is a key issue to…

Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a problem that becomes more severe when handling visual inputs, whose sequences typically contain many…

Video-conditioned audio generation, including Video-to-Sound (V2S) and Visual Text-to-Speech (VisualTTS), has traditionally been treated as distinct tasks, leaving the potential for a unified generative framework largely underexplored. In…

Speaker verification aims to verify whether an input speech corresponds to the claimed speaker, and conventionally, this kind of system is deployed based on single-stream scenario, wherein the feature extractor operates in full frequency…

Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…

Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence during training, while diffusion methods require multi-step…

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system. Delivering such a model presents…

Significant progress has been made in speaker dependent Lip-to-Speech synthesis, which aims to generate speech from silent videos of talking faces. Current state-of-the-art approaches primarily employ non-autoregressive sequence-to-sequence…