通过基于多假设的课程学习,准确的半监督自动语音识别用于普通和特征性演讲
Ka Hyun Park1, Junghun Kim2, U Kang1
1Department of CSE, Seoul National University, Seoul, Republic of Korea.
PloS one
|October 21, 2025
概括
本研究介绍了MOCA和MOCA-S,这是自动语音识别 (ASR) 的新型半监督方法. 这些模型通过减少对潜在不准确的伪标签的依赖,提高了普通和特征语音的转录精度.
科学领域:
- 人工智能的人工智能
- 语音处理 语音处理
- 机器学习 机器学习
背景情况:
- 自动语音识别 (ASR) 系统对于翻译和转录等应用至关重要.
- 目前的ASR模型专门用于普通或特征语音.
- 半监督学习由于标记语音数据的高成本和稀缺性而获得了吸引力.
研究的目的:
- 为普通和特征语音开发准确的半监督ASR模型.
- 解决以前半监督的ASR方法中伪标签的局限性.
- 为了提高ASR性能,特别是对于具有有限数据的特征性语音.
主要方法:
- 拟议的MOCA (基于多假设的课程学习为半监督的ASR) 对于普通话.
- 开发了MOCA-S用于特征语音,利用来自其他语音类型的数据.
- MOCA 和 MOCA-S 每个实例生成多个假设,以减轻伪标签依赖.
- 根据特征相关性,MOCA-S可以动态调整伪标签.
主要成果:
- 与现有模型相比,MOCA和MOCA-S在ASR准确度方面取得了显著的改进.
- 多假设方法有效地减少了对不准确伪标签的依赖.
- MOCA-S成功地利用了来自其他语音特征的数据来增强特征语音识别.
结论:
- 拟议的MOCA和MOCA-S框架为半监督的ASR提供了一个强大的解决方案.
- 这些方法提高了各种语音类型的转录精度,包括具有独特特征的语音类型.
- 该研究强调了多假设生成和跨特征数据利用在ASR中的有效性.
相关概念视频
01:28Automatic Processing and Automatic Social Behavior
213
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
213
01:22Multi-input and Multi-variable systems
385
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...
In the absence of...
385
01:30Classification of Signals
1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K