深度因果语音增强和识别使用高效的长期短期记忆反复神经网络.
Zhenqing Li1, Abdul Basit1, Amil Daraz1
1School of Information Science and Engineering, NingboTech University, Ningbo, China.
PloS one
|January 3, 2024
概括
这项研究引入了一个沙钟形长短期记忆 (LSTM) 网络,通过捕捉长期的时间依赖来改善语音增强和识别. 新的因果模型显著提高了语音可理解性和质量,同时降低了噪音条件下的文字错误率.
科学领域:
- 人工智能的人工智能
- 深度学习 (Deep Learning) 是一种深度学习.
- 语音处理 语音处理
背景情况:
- 长期短期记忆 (LSTM) 网络对于顺序数据是有效的,但与长期依赖性作斗争.
- 现有的深度神经网络 (DNN) 在准确处理杂的语音以进行增强和识别任务方面面临挑战.
- 因果关系和实时处理是实际语音应用的关键要求.
研究的目的:
- 提出一种新的沙钟形状的LSTM架构,能够在顺序数据中捕获长期时间相关性.
- 通过改善特征表示和解决梯度衰变来增强语音增强和识别性能.
- 开发一个适合实时语音处理的因果系统,而不依赖未来的信息.
主要方法:
- 开发了一个沙钟形的LSTM架构,具有减少的特征分辨率和跳过连接,以保存信息并防止梯度衰变.
- 将注意力机制纳入跳过连接,以强调关键的光谱特征和区域.
- 训练模型使用组合的光谱特征集和理想比率面具 (IRM) 作为演讲增强的训练目标.
主要成果:
- 在多个数据集中,拟议的LSTM模型在语音可理解性 (STOI) 中实现了高达18.33%的显著改进,在感知质量 (PESQ) 中达到32.9%的显著改进.
- 在可见和不可见的噪音条件下表现优于现有的DNN,包括基线LSTM,FDNN,CNN和GAN.
- 在自动语音识别 (ASR) 任务中降低了文字错误率 (WER),在杂的环境中平均WER达到15.13%.
结论:
- 拟议的沙钟形LSTM具有注意力和跳过连接,有效地捕捉长期的时间依赖性,以进行强大的语音处理.
- 该模型的因果性使其适用于实时应用,在语音增强和识别方面提供卓越的性能.
- 这种新的架构代表了对处理杂语音数据的深度学习的重大进步,提高了可理解性和识别精度.
相关概念视频
01:35Long-term Potentiation
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
01:25Long-term Potentiation
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when presynaptic neurons...
Hebbian LTP
LTP can occur when presynaptic neurons...
01:26Higher Mental Functions of Brain: Learning and Memory
Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or playing an...
01:22Chunking and Rehearsal in Sensory Memory
Improving short-term memory can be achieved through techniques like chunking and rehearsal. Chunking involves organizing information into larger, more manageable units. This technique is particularly useful for information that exceeds the typical memory span of between five and nine items. For instance, logging into an online account with a password like "ta89vq0179gz" involves grouping letters and numbers into three chunks—ta89, vq01, and 79gz. It makes large amounts of information more...
01:18Long-Term Memory
Long-term memory is a relatively permanent type of memory, capable of storing vast amounts of information over extended periods. Its storage capacity is generally considered unlimited.
Long-term memory can be categorized into two primary types: explicit and implicit memory. Explicit memory, also known as declarative memory, involves the conscious recollection of information that we deliberately try to remember, recall, and articulate. This type of memory encompasses specific facts, events, and...
Long-term memory can be categorized into two primary types: explicit and implicit memory. Explicit memory, also known as declarative memory, involves the conscious recollection of information that we deliberately try to remember, recall, and articulate. This type of memory encompasses specific facts, events, and...
01:07Elaborative Rehearsals
Elaborative rehearsal is a crucial cognitive strategy that strengthens information encoding in long-term memory by making meaningful connections between new data and pre-existing knowledge. This approach contrasts with maintenance rehearsal, which involves simple repetition without delving into the significance of the information. While maintenance rehearsal might temporarily keep information active in short-term memory, it is less effective for long-term retention.
The effectiveness of...
The effectiveness of...