Code-Switching ASR · অসমীয়া
Assamese Data for Code-Switching ASR
Recognising speech that switches between an Indian language and English several times per sentence. In Assamese, the binding constraint is usually dialect coverage and code-mixing, not raw hours.
- Language
- Assamese
- Primary metric
- Switch-point accuracy
- Typical volume
- 100-500 hours
Data profile required
- Genuinely code-mixed spontaneous speech
- Per-token language ID labels
- A fixed rule for script of English tokens
What Assamese adds to the requirement
- Assamese has the voiceless velar fricative /x/, unique among major Indian languages and routinely mis-modelled
- No retroflex-dental contrast in the way Hindi has it, so Hindi-derived phone sets over-generate
- Dialects to cover: Kamrupi, Goalparia, Upper Assam (Sibsagar standard), Barak Valley contact varieties
- Assamese speech mixes Hindi, English and Bengali, with substantial contact influence in Barak Valley and tea-garden communities.
Metrics to track
- Switch-point accuracy
- Mixed-utterance WER
- Language ID token accuracy
Failure modes
- Concatenating monolingual data and calling it code-mixed
- Leaving script conventions to individual annotators
For Assamese specifically: Extremely low-resource. Almost no spontaneous Assamese speech data exists publicly, and non-standard dialects have none.
Recommended cohort
Expect longer fielding times and higher per-hour cost than for Hindi or Marathi; the speaker pool with transcription-grade literacy is smaller.
| Dimension | Typical split | Why it matters for Assamese |
|---|---|---|
| Gender | 50 / 50 | Pitch range differences change acoustic model behaviour; unbalanced cohorts bias recognition |
| Age | 18-25: 30%, 26-40: 40%, 41-60: 30% | Older speakers retain conservative Assamese forms that younger urban speakers have lost |
| Region | Assam / Arunachal Pradesh / parts of Nagaland and Meghalaya and others | Dialect spread across 4 recognised varieties |
| Education | Mixed, including below-graduate | Prompt-reading fluency correlates with education and skews prosody |
| Condition | Studio / quiet room / field | Match the noise profile of your deployment |
Suggested programme shape
Start with an evaluation set of 80 speakers spread across every Assamese dialect in scope, collected before training data. Then field 100-500 hours of training data from disjoint speakers.
This ordering is what makes the improvement measurable rather than assumed.
Frequently asked
Is there usable public Assamese data for code-switching asr?
Extremely low-resource. Almost no spontaneous Assamese speech data exists publicly, and non-standard dialects have none.
How many Assamese speakers do we need?
300-800 speakers for a training corpus, plus a disjoint evaluation cohort covering each dialect. Speaker count matters more than hours for generalisation.
Can you run this across multiple languages at once?
Yes. Multi-language programmes run to one master specification so per-language results stay comparable.
Scope Assamese data for code-switching asr
Send the target metric and the languages in scope.