Performance Evaluation of Indonesian Language Forced Alignment Using Montreal Forced Aligner
Bibliographic record
Abstract
Manual segmentation is crucial for aligning words or phonemes between speech signals and their transcription. It is used in many applications, such as speech recognition, speaker diarization, and speech synthesis. However, because manual segmentation can be laborious and time-consuming, forced alignment algorithms are used to automate the process by aligning the speech audio to its corresponding text transcription at the phoneme or word level. To overcome this problem, one of the solutions is a forced alignment tool called Montreal Force Aligner. This tool has two requirements: a language acoustic model and a corresponding language dictionary. The challenges are determining a suitable recipe for training the model and achieving a good alignment with minimum error. In this study, training and evaluation are conducted for the Indonesian language using the Montreal Forced Aligner. A conversational corpus from a range of five to 30 speakers with various duration between one hour and two hours is used as an input to train the acoustic model. Then, the model is employed to align the conversational Indonesian corpus using the ASR-INDOCSC test set. Our findings include a recommendation training strategy for developing an Indonesian language acoustic model using the Montreal Forced Aligner tool, which measures the number of speakers and hours required.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.005 |
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 source (direct Gemma or distilled Codex), 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".