- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The authors propose a new loss function, PEAL, which computes a soft minimum over the costs of all possible edit paths aligning a predicted sequence with a target sequence. Insertions and deletions have fixed costs, while substitutions have a prediction-dependent cost of . The authors show that, under restrictive conditions, minimizing PEAL serves as a surrogate for minimizing empirical edit distance within a fixed hypothesis class. The loss can be used either as an auxiliary regularization term in a combined training objective or as a fine-tuning objective following initial training with another loss, such as CTC.
Critical strengths
One strength of the paper is that the proposed loss is supported by a theoretical analysis linking it to edit-distance minimization, although the result relies on very restrictive assumptions.
Critical weaknesses
Clarity of the theoretical presentation. The paper would benefit from explicitly defining terms such as empirical risk, excess risk, and H-consistency in the main text rather than in the appendices, or at least referring readers to the relevant appendix, which is currently not done. Since the paper is primarily application-oriented, these concepts should be clearly introduced to make the theoretical discussion accessible to a broader audience.
Motivation and positioning relative to existing work. The positioning of the paper with respect to existing alignment-based objectives is not entirely clear to me. The limitation of position-wise cross-entropy described by the authors is valid, but CE is already known to be poorly suited to tasks where the alignment between predictions and targets is unknown. This is precisely why objectives such as CTC and other alignment-aware losses have been introduced.
I therefore struggle to identify the specific limitation of these existing methods that PEAL aims to address. In the related work, the authors state that the implications of alignment-based objectives for "structured prediction capability require further analysis." However, it is unclear what is meant by structured prediction capability beyond the alignment and sequence-level prediction properties already addressed by these methods. Existing alignment-based losses have demonstrated strong empirical effectiveness, and the paper does not clearly explain what remains unresolved or how PEAL fundamentally differs in this respect.
The theoretical connection between PEAL and edit-distance minimization is interesting, but given the restrictive assumptions under which it is established, I am not convinced that it sufficiently addresses this motivation. A clearer comparison with existing alignment-based objectives would help establish the contribution.
Questions for authors
Justification for using soft-min smoothing: In Section 2.2, the authors justify the use of a soft minimum by stating that "Direct hard minimization is nondifferentiable when the minimum-cost path changes." Could the authors clarify this justification? As I understand it, the envelope theorem would allow one to first identify the minimum-cost alignment path and then compute a gradient step with respect to its cost, at least when the optimal path is unique. Why is soft-min smoothing preferred over this approach?
Choice of ASR dataset: Could the authors explain why they chose to evaluate ASR on a 24-minute subset of the Gronings dataset rather than on a more widely used benchmark such as LibriSpeech?
Handling of ASR alignments: How are blank tokens, repeated labels, and differences between acoustic-frame and target-sequence lengths handled? Is PEAL computed over all possible edit paths between the full frame-level predictions and the target sequence, or is some preprocessing applied?
15 comments
Part 2
W2
Motivation and positioning relative to existing work. The positioning of the paper with respect to existing alignment-based objectives is not entirely clear to me. The limitation of position-wise cross-entropy described by the authors is valid, but CE is already known to be poorly suited to tasks where the alignment between predictions and targets is unknown. This is precisely why objectives such as CTC and other alignment-aware losses have been introduced.
I therefore struggle to identify the specific limitation of these existing methods that PEAL aims to address. In the related work, the authors state that the implications of alignment-based objectives for "structured prediction capability require further analysis." However, it is unclear what is meant by structured prediction capability beyond the alignment and sequence-level prediction properties already addressed by these methods. Existing alignment-based losses have demonstrated strong empirical effectiveness, and the paper does not clearly explain what remains unresolved or how PEAL fundamentally differs in this respect.
The theoretical connection between PEAL and edit-distance minimization is interesting, but given the restrictive assumptions under which it is established, I am not convinced that it sufficiently addresses this motivation. A clearer comparison with existing alignment-based objectives would help establish the contribution.
Response
Thank you for these questions about PEAL's motivation and contribution.
PEAL aims to make further optimization build on correct sequence structure already present in a prediction. A locally shifted subsequence can contain useful learned content even when the complete prediction has missing or extra events. The central question is which parts of that prediction the training signal reinforces and which errors it penalizes. PEAL determines this signal through edit correspondences, allowing correct shifted matches to contribute positively while missing and surplus events remain charged. We address four aspects below. (1) We explain how existing alignment and sequence-training objectives assign supervision, and what PEAL changes in the resulting updates. (2) We measure the amount and continuity of correct structure retained in the predictions. (3) We test the contribution of edit correspondences through ablations, training trajectories, and comparisons with related objectives. (4) We connect the theoretical bounds to initialization, temperature selection, and the relationship between surrogate and edit-distance optima.
1. How the supervision changes subsequent optimization.
CTC [1] resolves unknown frame-to-label timing by summing the probabilities of paths that collapse exactly to the reference. It can reinforce correct shifted events through compatible frame-level paths. When retaining those events would require an insertion or deletion outside its collapse rules, however, that partial correspondence supplies no path to the CTC likelihood. Optimization then follows the available exact-transcription paths, which can assign different labels to the positions already supporting correct content.
Consider the target A B C D and four prediction positions favoring B C D X. The first three predictions already form a correct ordered subsequence. On this four-position grid, CTC has only one path collapsing to the four distinct target labels, namely A B C D, so each position is pushed toward its diagonal target. PEAL admits an edit path retaining the three matches B C D and charging for missing A and extra X. This path lets optimization strengthen the existing three-label subsequence without requiring those positions to first change their labels to obtain training credit.
This difference can be checked directly. Over , let each position assign probability 0.95 to its favored label and 0.01 to every other label. With and unit gap costs, the PEAL path retaining B C D costs , whereas the diagonal path costs . At , enumerating all 321 edit paths gives a negative logit gradient of approximately for each of these three correct labels. CTC gives a positive gradient of for each on the same grid, using unnormalized losses. Gradient descent thus reinforces B C D under PEAL and suppresses them under CTC in this example. In actual ASR training, CTC operates on the acoustic frames, where additional frames can support other exact-transcription alignments; PEAL adds edit supervision on the compact event sequence constructed in Q3.
Part 3
Soft-DTW [2] preserves ordered matches through repeated pairings that represent temporal stretching. For prediction A A B C and target A B C C, both predicted A events can match one target A, and the final predicted C can match both target C events (Appendix G.2, Figure 9). As these pairwise content costs approach zero, the warped path can have near-zero cost despite the extra A and missing C. Thus, further improving the matched content can leave an event-count error unrepresented in that path's cost. PEAL uses one-to-one matches and charges the remaining deletion and insertion. A prediction with correct content but incorrect event multiplicities consequently retains an edit penalty. Its gap costs also affect which competing matches receive gradient weight, keeping the supervision sensitive to event-count discrepancies as well as label agreement.
AXE [3] preserves shifted matches while supervising skipped predictions through and skipped targets through at an existing prediction. In the B C D X example, a path retaining B C D must still assign missing A to an existing prediction. If A and B share the position favoring B, that path contains both and . Increasing the probability of missing A then competes with strengthening the already correct B. PEAL charges for missing A without assigning it an additional likelihood target at the B position. On that edit path, the position receives matching supervision for B. This changes what the optimizer is asked to preserve during correction, and the retention measurements below assess the resulting sequence structure.
The resulting local signal is explicit. Let be the total Gibbs probability of paths pairing prediction with target . Sections 2.2–2.3 give
\qquad \frac{\partial L_\tau}{\partial p_{i,c}} =-\alpha(1-p_{i,c})^{\alpha-1}\sum_{j:y_j=c}A_{i,j}.$$ A correct shifted label receives support from paths matching it to its reference occurrence. When several low-cost paths share that match, their weights add; when they disagree, the competing correspondences contribute according to their complete path costs. Gap costs alter these weights and have zero direct probability derivatives. Consequently, PEAL can reinforce correspondences shared by plausible alignments while adapting supervision where they differ. This also distinguishes PEAL from methods that introduce edit-distance information at other stages of training. MRT [4] and normalized N-best MWER/EMBR [5] use a candidate's centered sequence error to weight its log-likelihood gradient. Under autoregressive factorization, the same scalar coefficient multiplies all token log-likelihood terms in that candidate. This weights the candidate's correct and incorrect parts together. For a fixed candidate set with equal errors, the centered risk gradient is zero, even though their probability assignments can still be improved. PEAL's probability-sensitive costs and pairwise marginals retain feedback about which reference labels each prediction supports. O-1 [6] selects an oracle and a 1-best candidate for error-weighted likelihood updates; its available supervision depends on those selected hypotheses. PEAL obtains its correspondence weights directly from the supplied probability matrix and reference. OCD [7] and prefix-based TLE [8] provide finer next-action feedback. OCD teaches optimal continuations after a generated prefix, and TLE learns scores from completion-loss increments. The supervision for a position is constructed from the prefix preceding it and the possible continuations. PEAL uses the complete current probability matrix, including downstream predictions, to decide which reference positions should supervise that position. It can therefore reinforce an earlier label because of its role in an ordered subsequence already supported by later predictions. This makes the correspondence information available to parallel prediction heads without introducing an autoregressive completion decoder. We will clarify these differences in supervision and their optimization consequences in the Introduction and Related Work.
Part 1
W1
Response
Thank you for suggesting clearer theoretical definitions.
We will state the risk definitions explicitly before Theorem 1 in Section 2.4 (Conditional Optimality Guarantees for PEAL) and connect them to the assumptions used in the theorem.
Empirical risk. Fix a sample set S=(xk,yk)k=1N and a nonempty class H of probabilistic predictors. In Theorem 1, prediction and target lengths are both n, and insertion and deletion costs are one. Let yh(x) be the position-wise argmax sequence, using a fixed tie-breaking rule. The normalized target loss and theoretical surrogate are
ℓE(h;x,y)=ndED(yh(x),y),ℓS,τ(h;x,y)=nLτ(h(x),y)+τlogKn,n,
where Kn,n is the number of valid edit paths. For either loss ℓ, empirical risk is its sample average, Rℓ(h)=N−1∑k=1Nℓ(h;xk,yk). The path-count correction is constant across H at fixed lengths. Consequently, the theoretical surrogate and practical normalized loss Lτ/n have identical empirical excess risks (Appendix H.2).
Excess risk. This is the difference in risk from the best value attainable within the same class,
Eℓ,H(h)=Rℓ(h)−infh′∈HRℓ(h′).
Using the same H for both losses makes the comparison about their preferred models within that class [9].
Conditional empirical H-consistency. For the fixed sample set and class, the guarantee means that any sequence of models (ht)⊂H with ES,τ,H(ht)→0 also satisfies EE,H(ht)→0. In our result, this follows from
EE,H(h)≤1−βξ,τ/gES,τ,H(h),βξ,τ<g,
where g is the smallest positive empirical edit-distance excess risk, when one exists, and βξ,τ is the uniform approximation width. Its confidence condition requires maxcph,i,c(xk)≥1−ξ for every h∈H, sample k, and position i, with 0<ξ<1/2. For N equally weighted samples of length n, unit edit costs give g≥1/(Nn), yielding the sufficient condition in Theorem 1.
Appendix H.1 defines the sequences, decoding rule, losses, and risks; H.2 relates the practical and theoretical objectives; K derives the approximation bounds; and L proves the excess-risk transfer. The fixed unequal-length extension is described in the response to W2 below.