Results 121 to 130 of about 3,240 (204)

Multi-Label Emotion Recognition of Korean Speech Data Using Deep Fusion Models

Applied Sciences
As speech is the most natural way for humans to express emotions, studies on Speech Emotion Recognition (SER) have been conducted in various ways However, there are some areas for improvement in previous SER studies: (1) while some studies have performed
Seoin Park, Byeonghoon Jeon, Seunghyun Lee, Janghyeok Yoon   +3 more
doaj   +1 more source

Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Discrete audio representation, aka audio tokenization, has seen renewed interest driven by its potential to facilitate the application of text language modeling approaches in audio domain. To this end, various compression and representation-learning based tokenization schemes have been proposed.
Krishna C. Puvvada, Nithin Rao Koluguri, Kunal Dhawan, Jagadeesh Balam, Boris Ginsburg   +4 more
openaire   +2 more sources

Research on Speech Enhancement Translation and Mel-Spectrogram Mapping Method for the Deaf Based on Pix2PixGANs

IEEE Access
This study proposes an innovative speech translation method based on Pix2PixGAN, which maps the Mel spectrograms of speech produced by deaf individuals to those of normal-hearing individuals and generates semantically coherent speech output.
Shaoting Zeng, Xinran Xu, Xinyu Chi, Yuqing Liu, Huiting Yu, Feng Zou   +5 more
doaj   +1 more source

SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG

ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Decoding speech from brain signals is a challenging research problem that holds significant importance for studying speech processing in the brain. Although breakthroughs have been made in reconstructing the mel spectrograms of audio stimuli perceived by subjects at the word or letter level using noninvasive electroencephalography (EEG), there is still
Cunhang Fan, Sheng Zhang, Jingjing Zhang, Zexu Pan, Zhao Lv   +4 more
openaire   +2 more sources

Klasifikasi Pengucapan Huruf Hijaiyah Berbasis Android Menggunakan CNN dengan Fitur Mel-Spectrogram

Mastery of Hijaiyah letters is a fundamental basis in learning the Qur'an, but data from the IIQ Community Service Institute 2021/2022 shows that 72.25% of the 3,111 Muslims tested have not been able to read the Qur'an properly.
Listyorini, Tri, Muqsith, Fawwaz Ijlal, Supriyati, Endang   +2 more
core   +1 more source

LungNeXt: A novel lightweight network utilizing enhanced mel-spectrogram for lung sound classification

Lung auscultation is essential for early lung condition detection. Categorizing adventitious lung sounds requires expert discrimination by medical specialists.
Yue Liu, Xiaochen Yuan, Chan-Tong Lam, Fan Wang   +3 more
core   +1 more source

Exhaustive benchmark of architectural variations with respect to the logmelspec-CNN baseline, on a task of binary classification of presence vs. absence of a bird in audio clips.

, 2019
Dot colors represent folds in BirdVox-70k. GDA: geometrical data augmentation. logmelspec: log-mel-spectrogram. PCEN: per-channel energy normalization. MoE: mixture of experts. AT: adaptive threshold.
Andrew Farnsworth (401325), Steve Kelling (337133), Vincent Lostanlen (5803529), Juan Pablo Bello (3359759), Justin Salamon (634133)   +4 more
core   +1 more source

Spectrogram Features for Audio and Speech Analysis

Applied Sciences
Spectrogram-based representations have grown to dominate the feature space for deep learning audio analysis systems, and are often adopted for speech analysis also.
Ian McLoughlin, Lam Pham, Yan Song, Xiaoxiao Miao, Huy Phan, Pengfei Cai, Qing Gu, Jiang Nan, Haoyu Song, Donny Soh   +9 more
doaj   +1 more source

Audio Conversion for Music Genre Classification Using Short-Time Fourier Transform and Inception V3

Jurnal Elkomika
This research examines the development of music genres and technological applications in music genre recognition through the MIR (Music Information Retrieval) approach.
DEWI ROSMALA, MOHAMMAD NOER FADHILAH
doaj   +1 more source

VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature

The mainstream neural text-to-speech(TTS) pipeline is a cascade system, including an acoustic model(AM) that predicts acoustic feature from the input transcript and a vocoder that generates waveform according to the given acoustic feature.
Du, Chenpeng, Guo, Yiwei, Chen, Xie, Yu, Kai   +3 more
core   +2 more sources