强大的序列对序列语音转换,用于在噪音和反响条件下增强电喉语音
概括
本研究引入了使用序列到序列模型将电喉 (EL) 语音转换为正常语音 (EL2SP) 的新训练方法. 这种方法显著提高了人工语音的可理解性和自然性,即使有背景噪音.
科学领域:
- 语音处理 语音处理
- 人工智能的人工智能
- 生物医学工程 生物医学工程
背景情况:
- 电喉 (EL) 语音,由喉切除术所使用,由于与正常语音的音调和时间差异,缺乏自然性和可理解性.
- 现有的语音转换 (VC) 模型用于EL语音到正常语音 (EL2SP) 主要集中在清洁的语音上,限制了现实世界的应用.
研究的目的:
- 开发用于序列对序列 (seq2seq) VC模型的新型培训技术,以提高EL2SP在现实环境中的稳定性.
- 为了提高人造语言的自然性和可理解性,为那些经历了喉切除术的个人.
主要方法:
- 使用文本转语音模型预训练一个正常到正常的seq2seq VC模型.
- 使用人工生成的噪音和反响EL语音数据实施两阶段的微调过程.
- 调查各种设计选项,以评估拟议方法的有效性.
主要成果:
- 拟议的方法显示了EL2SP性能的显著改善.
- 这种方法有效地处理了干净和噪音响应的EL语音.
- 在现实场景中实现了EL2SP的增强稳定性.
结论:
- 新的培训技术提高了seq2seq VC对EL2SP的稳定性.
- 该方法通过结合噪音和反响条件,成功地解决了以前的EL2SP方法的局限性.
- 这项研究有助于在不同的环境中为喉切除器进行更自然和更易理解的人工语言.
更多相关视频
09:09Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
385
06:24Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications
Published on: January 5, 2024
748
相关概念视频
Design Example: Vintage Mixing Console
197
A sound engineer at a music company recently encountered a problem. The output from their newly acquired studio's vintage mixing console was too low for the requirements of modern recording equipment. To rectify this situation, the engineer decided to design an audio pre-amplifier using an operational amplifier (op-amp) to boost the signal level.
The specifications for the pre-amplifier were clear. It needed to amplify the audio signal by a factor of 10, have an input impedance above 10...
The specifications for the pre-amplifier were clear. It needed to amplify the audio signal by a factor of 10, have an input impedance above 10...
197
Double Resonance Techniques: Overview
176
Double resonance techniques in Nuclear Magnetic Resonance (NMR) spectroscopy involve the simultaneous application of two different frequencies or radiofrequency pulses to manipulate and observe two distinct nuclear spins. One important application of double resonance is spin decoupling, which selectively suppresses coupling with one type of nucleus while observing the NMR signal from another nucleus, simplifying the spectrum and enhancing resolution.
Spin decoupling is usually achieved by...
Spin decoupling is usually achieved by...
176
Lossy Lines and Overvoltages
77
Transmission-line series resistance and shunt conductance cause three primary effects: attenuation, distortion, and power losses.
Attenuation
When constant series resistance and shunt conductance are present, voltage and current equations are modified. The propagation constant indicates that voltage and current waves consist of both forward and backward traveling components. These waves attenuate as they propagate, with the attenuation factor related to the resistance and conductance. In a...
Attenuation
When constant series resistance and shunt conductance are present, voltage and current equations are modified. The propagation constant indicates that voltage and current waves consist of both forward and backward traveling components. These waves attenuate as they propagate, with the attenuation factor related to the resistance and conductance. In a...
77
Design Example
312
The innovation of touch-tone telephony revolutionized the telecommunications industry by replacing the traditional rotary dial with a dual-tone multi-frequency (DTMF) signaling system. This system uses a matrix-style keypad with buttons arranged in four rows and three columns, creating 12 distinct signals each assigned to a pair of frequencies. Each button press results in a simultaneous generation of two sinusoidal tones – one from a low-frequency group (697 to 941 Hz) and one from a...
312
Reconstruction of Signal using Interpolation
157
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
157
