Related Concept Videos
Language Development
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
Components of Language
Language and Cognition
Automatic Processing and Automatic Social Behavior
Higher Mental Functions of the Brain: Language
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
Elaborative Rehearsals
The effectiveness of...
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
RETRACTION: Real-Time Modulation of Physical Training Intensity Based on Wavelet Recursive Fuzzy Neural Networks.
RETRACTION: Multidimensional Heterogeneous Network Link Adaptation Based on Mobile Environment.
RETRACTION: Framework to Segment and Evaluate Multiple Sclerosis Lesion in MRI Slices Using VGG-UNet.
RETRACTION: Facial Emotion Recognition Using a Novel Fusion of Convolutional Neural Network and Local Binary Pattern in Crime Investigation.
RETRACTION: Automatic Intelligent System Using Medical of Things for Multiple Sclerosis Detection.
RETRACTION: Intangible Cultural Heritage Reproduction and Revitalization: Value Feedback, Practice, and Exploration Based on the IPA Model.
Related Experiment Video
Updated: Oct 1, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
Published on: August 9, 2024
RNN Language Processing Model-Driven Spoken Dialogue System Modeling Method.
1Foreign Language Department, Guangzhou Huashang College, Guangdong 511300, China.
This study improves spoken language understanding (SLU) in spoken dialogue systems (SDS) by using Recurrent Neural Network (RNN) language models to rescore recognition results. This method enhances accuracy, especially when test data differs from training data.
More Related Videos
Area of Science:
- Natural Language Processing
- Artificial Intelligence
- Speech Technology
Background:
- Spoken dialogue systems (SDS) rely heavily on accurate speech recognition and semantic understanding for effective performance.
- Improving spoken language understanding (SLU) is crucial for advancing SDS capabilities.
Purpose of the Study:
- To enhance the accuracy of SLU in SDS by optimizing the language model's performance.
- To address the challenge of data mismatch between training and testing sets in speech recognition.
Main Methods:
- Utilized Recurrent Neural Network (RNN) language models to predict text sequences.
- Introduced RNN language model probability scores to rescore intermediate recognition results.
- Proposed a cache RNN model combination to optimize decoding and improve word sequence probability calculations.
Main Results:
- The proposed method significantly improved the performance of the speech recognition system on test data.
- Demonstrated the potential for achieving higher SLU scores through the implemented approach.
Conclusions:
- The developed method effectively enhances speech recognition accuracy, particularly for unseen data.
- This research offers valuable insights for future advancements in spoken dialogue systems and SLU.

