Module align 

Exact forced alignment against a known reference.

The reference is a sequence of N phone columns and the acoustic model has scored T frames. Alignment assigns frames to phones by searching a single chain rather than a lattice of possible transcripts.

Chain topology

States s_0 … s_N, where s_i means “the first i phones are behind us”. s_0 is the start, s_N is the only final state, and four transitions leave each state, every one of them consuming exactly one frame:

transition	reads	goes to	costs	means
hold blank	blank	s_i	0	silence, or phone i + 1 has not started
hold phone	phone i	s_i	0	phone i is still sounding (i ≥ 1)
commit	phone i + 1	s_{i+1}	0	phone i + 1 starts in this frame
skip	blank	s_{i+1}	skip(i + 1)	phone i + 1 never happens

A skip makes a phone optional at a caller-supplied cost. Skipping is disabled by default; see AlignChain::with_skip_costs.

Exact search

Every transition consumes one frame and advances at most one phone. A path of T frames can therefore occupy position i at frame t only when t - (T - N) <= i <= t. band covers exactly those reachable cells, so align needs no beam or pruning threshold.

The solver reads the original acoustic columns directly. It does not widen the score matrix to distinguish transitions that read the same phone or blank column, and it stores the four transition codes in two bits each.

Custom topologies

trellis supplies the banded Viterbi and forward-backward solvers independently of this chain. Implement Trellis for constraints such as minimum duration or multi-phone skips. AlignChain::against exposes this module’s trellis when the raw Path or posteriors are needed.

Structs

AlignChain

A reference to align: the phones in order, and what each one costs to give up.

Alignment

Which phone each frame sounded.

ChainTrellis

AlignChain against a matrix of scores: the trellis align solves.

Functions

align

Aligns chain to dense: the best path of the chain against the acoustic scores, exactly.