Enhanced Dialectal Speech Recognition in Punjabi Using Pitch-Based Acoustic Modeling
Bibliographic record
Abstract
Automatic Speech Recognition (ASR) systems usually have difficulty accurately transcribing dialectal variations, resulting in subpar performance in areas where dialectal variants are common.The pitch-based Dialect ASR method we described in this paper aims to improve voice recognition for dialectal differences of Punjabi language.We use the pitch information that was taken out of the voice signal as a feature to enhance the dialectal nuance recognition.The suggested system includes a cutting-edge pitch-based feature extraction module that records minute differences in pitch patterns linked to various dialects.This module gives the ASR system the ability to distinguish between phonetic units more effectively and faithfully depict the distinguishing features of dialectal speech.To develop reliable representations from the pitch-based data, we also use deep learning approaches, speaker adaptive training, and vocal-tract length normalization (VTLN).The experimental results show the significant reduction in the WER of 6.63% and 4.98% for Malwa and Majha dialects.Language learning applications could benefit from the developed Punjabi dialectal speech recognition system by offering learners exposure to various dialects and accents.This can help learners develop a well-rounded understanding of the language and better adapt to different regional variations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.004 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".