Quiz 2
Registry Synced

Learning Objectives

427 words
2 min read

Reading compass

Now · 1. ASR Architecture

Learning Objectives

  • Understand ASR system architecture
  • Apply decoding and search algorithms
  • Evaluate ASR performance
  • Weeks 4-5: HMMs and GMMs
  • Understanding of probability

1. ASR Architecture

Components:
  1. Front-end: Feature extraction (MFCCs)
  2. Acoustic Model: GMM-HMM (P(X|W) - probability of features given words)
  3. Pronunciation Dictionary: Word -> phoneme sequence mapping
  4. Language Model: Word sequence probability (P(W))
  5. Decoder: Combine acoustic + language models to find most likely word sequence

2. Decoding

Viterbi Beam Search: Dynamic programming search through state space. Maintains beam of active hypotheses at each time step. Prunes low-probability paths to maintain tractability. Token Passing: Each hypothesis carries accumulated score, history (word sequence), and current HMM state. Language Model Integration: Acoustic score + word penalty + language model score (log probabilities).

3. Performance Metrics

Word Error Rate (WER):
WER=S+D+IN×100%WER = \frac{S + D + I}{N} \times 100\%
S = substitutions, D = deletions, I = insertions, N = reference words Real-Time Factor (RTF): Processing time / audio duration. RTF < 1 = faster than real-time.
Q1: What are the 5 components of an ASR system?
Feature extraction (MFCCs), Acoustic model (GMM-HMM/DNN), Pronunciation dictionary (word->phonemes), Language model (n-gram/neural), Decoder (Viterbi beam search). Q2: How is Word Error Rate calculated?
WER = (Substitutions + Deletions + Insertions) / Reference Word Count. Minimum between reference and hypothesis using dynamic programming (Levenshtein distance). 0% = perfect, ~5% = human parity, >30% = poor. Q3: What is beam search in ASR decoding?
Pruning technique: at each time step, only keep top-B hypotheses (by cumulative score). Reduces search space from exponential to O(B*T). Trade-off: narrow beam = faster but may miss correct path. Q4: What is the role of the pronunciation dictionary?
Maps words to phoneme sequences (e.g., "speech" -> /s p iy ch/). Handles multiple pronunciations ("either" -> /iy dh er/ or /ay dh er/). Typically 100k+ words for English. Q5: What is a language model weight (LMW) in ASR?
Scale factor applied to LM score during decoding. Optimal value (~10-20) balances acoustic and language model contributions. Higher weight = more constrained (better for narrow domain). Lower = more open (better for general). Q6: How to reduce WER?
More training data, better features (MFCC + delta + speaker normalization), more context (triphones), better acoustic models (DNN), stronger language models (neural LM), speaker adaptation (fMLLR), data augmentation (noise, speed perturbation). Join Discord PreviousGaussian Mixture Models & Acoustic ModelingNextDeep Learning for ASR
Document outline

Keep your place and jump directly to a heading.

Table of Contents
System Normal // Awaiting Context

Intelligence Hub

Navigate the knowledge graph to generate context. The Hub adapts dynamically to surface backlinks, related notes, and metadata insights.