相关论文: MooseNet: A Trainable Metric for Synthesized Speec…

Self-supervised learning (SSL) using masked prediction has made great strides in general-purpose audio representation. This study proposes Masked Modeling Duo (M2D), an improved masked prediction SSL, which learns by predicting…

In speech synthesis and speech enhancement systems, melspectrograms need to be precise in acoustic representations. However, the generated spectrograms are over-smooth, that could not produce high quality synthesized speech. Inspired by…

Recently, discrete tokens derived from self-supervised learning (SSL) models via k-means clustering have been actively studied as pseudo-text in speech language models and as efficient intermediate representations for various tasks.…

Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language…

We explore the possibility of leveraging accelerometer data to perform speech enhancement in very noisy conditions. Although it is possible to only partially reconstruct user's speech from the accelerometer, the latter provides a strong…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

We propose TalkNet, a non-autoregressive convolutional neural model for speech synthesis with explicit pitch and duration prediction. The model consists of three feed-forward convolutional networks. The first network predicts grapheme…

This paper presents a speech intelligibility model based on automatic speech recognition (ASR), combining phoneme probabilities from deep neural networks (DNN) and a performance measure that estimates the word error rate from these…

Conventional automatic speaker verification systems can usually be decomposed into a front-end model such as time delay neural network (TDNN) for extracting speaker embeddings and a back-end model such as statistics-based probabilistic…

Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative…

We present an approach to tackle the speaker recognition problem using Triplet Neural Networks. Currently, the $i$-vector representation with probabilistic linear discriminant analysis (PLDA) is the most commonly used technique to solve…

This work introduces an approach to assessing phrase break in ESL learners' speech with pre-trained language models (PLMs). Different with traditional methods, this proposal converts speech to token sequences, and then leverages the power…

Training of multi-speaker text-to-speech (TTS) systems relies on curated datasets based on high-quality recordings or audiobooks. Such datasets often lack speaker diversity and are expensive to collect. As an alternative, recent studies…

This study demonstrates that a Multimodal Large Language Model (MLLM) adapted via Low-Rank Adaptation (LoRA) can perform both Automatic Pronunciation Assessment (APA) and Mispronunciation Detection and Diagnosis (MDD) simultaneously.…

We introduce our submission to the AudioMOS Challenge (AMC) 2025 Track 3: mean opinion score (MOS) prediction for speech with multiple sampling frequencies (SFs). Our submitted model integrates an SF-independent (SFI) convolutional layer…

State-of-the-art text-to-speech (TTS) systems have utilized pretrained language models (PLMs) to enhance prosody and create more natural-sounding speech. However, while PLMs have been extensively researched for natural language…

Continuous speech can be converted into a discrete sequence by deriving discrete units from the hidden features of self-supervised learned (SSL) speech models. Although SSL models are becoming larger and trained on more data, they are often…

Dialogue state tracking (DST) aims to convert the dialogue history into dialogue states which consist of slot-value pairs. As condensed structural information memorizing all history information, the dialogue state in the last turn is…

In this paper, we address the problem of speaker verification in conditions unseen or unknown during development. A standard method for speaker verification consists of extracting speaker embeddings with a deep neural network and processing…

This article presents a probabilistic generative model for text based on semantic topics and syntactic classes called Part-of-Speech LDA (POSLDA). POSLDA simultaneously uncovers short-range syntactic patterns (syntax) and long-range…