相关论文: Streaming on-device detection of device directed s…

Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command. To make interactions with the assistant more intuitive, we explore whether it is feasible to drop the requirement that users…

The wide deployment of speech-based biometric systems usually demands high-performance speaker recognition algorithms. However, most of the prior works for speaker recognition either process the speech in the frequency domain or time…

Real-time voice agents face a dilemma: end-to-end models often lack deep reasoning, while cascaded pipelines incur high latency by executing ASR, LLM reasoning, and TTS strictly in sequence, unlike human conversation where listeners often…

A promising approach for steering auditory attention in complex listening environments relies on Auditory Attention Decoding (AAD), which aim to identify the attended speech stream in a multiple speaker scenario from neural recordings.…

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

Voice-triggered smart assistants often rely on detection of a trigger-phrase before they start listening for the user request. Mitigation of false triggers is an important aspect of building a privacy-centric non-intrusive smart assistant.…

Modern Text-to-Speech (TTS) systems increasingly leverage Large Language Model (LLM) architectures to achieve scalable, high-fidelity, zero-shot generation. However, these systems typically rely on fixed-frame-rate acoustic tokenization,…

Nowadays more and more applications can benefit from edge-based text-to-speech (TTS). However, most existing TTS models are too computationally expensive and are not flexible enough to be deployed on the diverse variety of edge devices with…

This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of…

In this paper, we exploit a Fully Convolutional Network (FCN) to analyze the audio data of spontaneous speech for dementia detection. A fully convolutional network accommodates speech samples with varying lengths, thus enabling us to…

In this paper, we describe the work that we have done to participate in Task1 of the ConferencingSpeech2021 challenge. This task set a goal to develop the solution for multi-channel speech enhancement in a real-time manner. We propose a…

Automated detection of voice disorders with computational methods is a recent research area in the medical domain since it requires a rigorous endoscopy for the accurate diagnosis. Efficient screening methods are required for the diagnosis…

We propose a stacked 1D convolutional neural network (S1DCNN) for end-to-end small footprint voice trigger detection in a streaming scenario. Voice trigger detection is an important speech application, with which users can activate their…

Agent assistance during human-human customer support spoken interactions requires triggering workflows based on the caller's intent (reason for call). Timeliness of prediction is essential for a good user experience. The goal is for a…

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…

This paper tackles several challenges that arise when integrating Automatic Speech Recognition (ASR) and Machine Translation (MT) for real-time, on-device streaming speech translation. Although state-of-the-art ASR systems based on…

Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of…

This paper integrates a voice activity detection (VAD) function with end-to-end automatic speech recognition toward an online speech interface and transcribing very long audio recordings. We focus on connectionist temporal classification…

The time delay neural network (TDNN) represents one of the state-of-the-art of neural solutions to text-independent speaker verification. However, they require a large number of filters to capture the speaker characteristics at any local…

In this paper, we introduce a novel language identification system based on conformer layers. We propose an attentive temporal pooling mechanism to allow the model to carry information in long-form audio via a recurrent form, such that the…