IEEE/ACM Transactions on Audio Speech and Language Processing

You are here

Home » Publications & Resources » Publications » IEEE/ACM Transactions on Audio Speech and Language Processing

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

Scope

The IEEE/ACM Transactions on Audio, Speech, and Language Processing is dedicated to innovative theory and methods for processing signals representing audio, speech and language, and their applications. This includes analysis, synthesis, enhancement, transformation, classification and interpretation of such signals as well as the design, development, and evaluation of associated signal processing systems.

Machine learning and pattern analysis applied to any of the above areas is also welcome.

Reproducible research

The Transactions encourages authors to make their publications reproducible by making all information needed to reproduce the presented results available online. This typically requires publishing the code and data used to produce the publication's figures and tables on a website; see the supplemental materials section of the information for authors. It gives other researchers easier access to the work, and facilitates fair comparisons.

Multimedia content

It is now possible to submit for review and publish in Xplore supporting multimedia material such as speech samples, images, movies, matlab code etc. A multimedia graphical abstract can also be displayed along with the traditional text. More information is available under Multimedia Materials at the IEEE Author Center.

TASLP Volume 32 | 2024

Disentangling Prosody Representations With Unsupervised Speech Reconstruction

TASLP Volume 32 | 2024
TASLP Articles

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity in speech recognition and speaker verification tasks respectively. However, it is still an open challenging question to extract prosodic information because of the intrinsic association of different attributes, such as timbre and rhythm, and because of the need for supervised training schemes to achieve robust speech recognition.

Read More ›

Speech Dereverberation With Frequency Domain Autoregressive Modeling

TASLP Volume 32 | 2024
TASLP Articles

Speech applications in far-field real world settings often deal with signals that are corrupted by reverberation. The task of dereverberation constitutes an important step to improve the audible quality and to reduce the error rates in applications like automatic speech recognition (ASR). We propose a unified framework of speech dereverberation for improving the speech quality and the ASR performance using the approach of envelope-carrier decomposition provided by an autoregressive (AR) model.

Read More ›

Operation-Augmented Numerical Reasoning for Question Answering

TASLP Volume 32 | 2024
TASLP Articles

Question answering requiring numerical reasoning, which generally involves symbolic operations such as sorting, counting, and addition, is a challenging task. To address such a problem, existing mixture-of-experts (MoE)-based methods design several specific answer predictors to handle different types of questions and achieve promising performance. However, they ignore the modeling and exploitation of fine-grained reasoning-related operations to support numerical reasoning, encountering the inadequacy in reasoning capability and interpretability.

Read More ›

Statistical Analysis for Speaker Recognition Evaluation With Data Dependence and Three Score Distributions

TASLP Volume 32 | 2024
TASLP Articles

The speaker recognition evaluation is conducted in a framework in which three score distributions and two decision thresholds are employed, and the statistic of interest is an average of the two weighted sums of the probabilities of type I and type II errors at the two thresholds correspondingly. And data dependence caused by multiple use of the same subjects exists ubiquitously in order to generate more samples because of limited resources.

Read More ›

SPS Social Media

IEEE SPS Educational Resources

IEEE SPS Resource Center

IEEE SPS YouTube Channel